Merge pull request #377 from CJackHwang/codex/run-all-tests-and-fix-failures

Fix failing current-input token accounting test

API.en.md

@@ -165,6 +165,8 @@ Gemini-compatible clients can also send `x-goog-api-key`, `?key=`, or `?api_key=
 | PUT | `/admin/chat-history/settings` | Admin | Update conversation history retention limit |
 | GET | `/admin/version` | Admin | Check current version and latest Release |
 
+OpenAI `/v1/*` paths are canonical. For clients configured with the bare DS2API service URL, the same OpenAI handlers are also exposed through root shortcuts: `/models`, `/models/{id}`, `/chat/completions`, `/responses`, `/responses/{response_id}`, `/embeddings`, and `/files`.
+
 ---
 
 ## Health Endpoints
@@ -199,8 +201,7 @@ No auth required. Returns the currently supported DeepSeek native model list.
     {"id": "deepseek-v4-pro", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
     {"id": "deepseek-v4-flash-search", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
     {"id": "deepseek-v4-pro-search", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
-    {"id": "deepseek-v4-vision", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
-    {"id": "deepseek-v4-vision-search", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []}
+    {"id": "deepseek-v4-vision", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []}
   ]
 }
 ```
@@ -224,6 +225,8 @@ Built-in aliases come from `internal/config/models.go`; `config.model_aliases` c
 - Gemini: `gemini-2.5-pro`, `gemini-2.5-flash`, `gemini-pro-vision`
 - Other compatibility families: `llama-*`, `qwen-*`, `mistral-*`, and `command-*` fall back through family heuristics
 
+Current vision support resolves only to `deepseek-v4-vision` and does not expose a separate `vision-search` variant.
+
 Retired historical families such as `claude-1.*`, `claude-2.*`, `claude-instant-*`, and `gpt-3.5*` are explicitly rejected.
 
 ### `POST /v1/chat/completions`
@@ -917,12 +920,15 @@ Updates proxy binding for a specific account.
   "message": "API test successful (session creation only)",
   "model": "deepseek-v4-flash",
   "session_count": 0,
-  "config_writable": true
+  "config_writable": true,
+  "config_warning": ""
 }
 ```
 
 If a `message` is provided, `thinking` may also be included when the upstream response carries reasoning text.
 
+When the configured file path is not writable (for example, read-only `/app/config.json` inside some containers), login/session testing still proceeds; `config_warning` is returned to indicate token persistence failed and the token is memory-only until restart.
+
 ### `POST /admin/accounts/test-all`
 
 Optional request field: `model`.

API.md

@@ -165,6 +165,8 @@ Gemini 兼容客户端还可以使用 `x-goog-api-key`、`?key=` 或 `?api_key=`
 | PUT | `/admin/chat-history/settings` | Admin | 更新对话记录保留条数 |
 | GET | `/admin/version` | Admin | 查询当前版本与最新 Release |
 
+OpenAI `/v1/*` 仍是规范路径。对于只配置 DS2API 根地址的客户端，同一套 OpenAI handler 也通过根路径快捷路由暴露：`/models`、`/models/{id}`、`/chat/completions`、`/responses`、`/responses/{response_id}`、`/embeddings`、`/files`。
+
 ---
 
 ## 健康检查
@@ -204,9 +206,7 @@ Gemini 兼容客户端还可以使用 `x-goog-api-key`、`?key=` 或 `?api_key=`
     {"id": "deepseek-v4-pro-search", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
     {"id": "deepseek-v4-pro-search-nothinking", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
     {"id": "deepseek-v4-vision", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
-    {"id": "deepseek-v4-vision-nothinking", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
-    {"id": "deepseek-v4-vision-search", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []},
-    {"id": "deepseek-v4-vision-search-nothinking", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []}
+    {"id": "deepseek-v4-vision-nothinking", "object": "model", "created": 1677610602, "owned_by": "deepseek", "permission": []}
   ]
 }
 ```
@@ -232,6 +232,7 @@ Gemini 兼容客户端还可以使用 `x-goog-api-key`、`?key=` 或 `?api_key=`
 - 其他兼容族：`llama-*`、`qwen-*`、`mistral-*`、`command-*` 会按家族启发式回退
 
 上述 alias 若在请求名后追加 `-nothinking` 后缀，也会映射到对应的强制关闭 thinking 版本。
+当前视觉能力仅对应 `deepseek-v4-vision` / `deepseek-v4-vision-nothinking`，不会解析出独立的 `vision-search` 变体。
 
 退役历史模型（如 `claude-1.*`、`claude-2.*`、`claude-instant-*`、`gpt-3.5*`）会被显式拒绝。
 
@@ -934,12 +935,15 @@ data: {"type":"message_stop"}
   "message": "API 测试成功（仅会话创建）",
   "model": "deepseek-v4-flash",
   "session_count": 0,
-  "config_writable": true
+  "config_writable": true,
+  "config_warning": ""
 }
 ```
 
 如果传入 `message`，还会附带 `thinking`（当上游返回思考内容时）。
 
+当部署环境配置文件路径不可写（例如容器内默认 `/app/config.json` 只读）时，登录与会话测试仍可继续；此时会返回 `config_warning` 提示 token 仅保存在内存、重启后丢失。
+
 ### `POST /admin/accounts/test-all`
 
 可选请求字段：`model`

Dockerfile

@@ -28,6 +28,8 @@ FROM debian:bookworm-slim AS runtime-base
 WORKDIR /app
 RUN apt-get update \
     && apt-get install -y --no-install-recommends ca-certificates \
+    && groupadd -r ds2api && useradd -r -g ds2api -d /app -s /sbin/nologin ds2api \
+    && mkdir -p /app/data && chown -R ds2api:ds2api /app \
     && rm -rf /var/lib/apt/lists/*
 COPY --from=busybox-tools /bin/busybox /usr/local/bin/busybox
 EXPOSE 5001
@@ -36,8 +38,9 @@ CMD ["/usr/local/bin/ds2api"]
 FROM runtime-base AS runtime-from-source
 COPY --from=go-builder /out/ds2api /usr/local/bin/ds2api
 
-COPY --from=go-builder /app/config.example.json /app/config.example.json
-COPY --from=webui-builder /app/static/admin /app/static/admin
+COPY --from=go-builder --chown=ds2api:ds2api /app/config.example.json /app/config.example.json
+COPY --from=webui-builder --chown=ds2api:ds2api /app/static/admin /app/static/admin
+USER ds2api
 
 FROM busybox-tools AS dist-extract
 ARG TARGETARCH
@@ -60,7 +63,8 @@ RUN set -eux; \
 FROM runtime-base AS runtime-from-dist
 COPY --from=dist-extract /out/ds2api /usr/local/bin/ds2api
 
-COPY --from=dist-extract /out/config.example.json /app/config.example.json
-COPY --from=dist-extract /out/static/admin /app/static/admin
+COPY --from=dist-extract --chown=ds2api:ds2api /out/config.example.json /app/config.example.json
+COPY --from=dist-extract --chown=ds2api:ds2api /out/static/admin /app/static/admin
+USER ds2api
 
 FROM runtime-from-source AS final

README.MD

@@ -31,6 +31,30 @@
 >
 > 请勿将本项目用于违反服务条款、协议、法律法规或平台规则的场景。商业使用前请自行确认 `LICENSE`、相关协议以及你是否获得了作者的书面许可。
 
+## 目录
+
+- [架构概览（摘要）](#架构概览摘要)
+- [核心能力](#核心能力)
+- [平台兼容矩阵](#平台兼容矩阵)
+- [模型支持](#模型支持)
+  - [OpenAI 接口](#openai-接口get-v1models)
+  - [Claude 接口](#claude-接口get-anthropicv1models)
+  - [Gemini 接口](#gemini-接口)
+- [快速开始](#快速开始)
+  - [方式一：下载 Release 构建包](#方式一下载-release-构建包)
+  - [方式二：Docker 运行](#方式二docker-运行)
+  - [方式三：Vercel 部署](#方式三vercel-部署)
+  - [方式四：本地源码运行](#方式四本地源码运行)
+- [配置说明](#配置说明)
+- [鉴权模式](#鉴权模式)
+- [并发模型](#并发模型)
+- [Tool Call 适配](#tool-call-适配)
+- [本地开发抓包工具](#本地开发抓包工具)
+- [文档索引](#文档索引)
+- [测试](#测试)
+- [Release 自动构建（GitHub Actions）](#release-自动构建github-actions)
+- [免责声明](#免责声明)
+
 ## 架构概览（摘要）
 
 ```mermaid
@@ -107,6 +131,8 @@ flowchart LR
 | WebUI 管理台 | `/admin` 单页应用（中英文双语、深色模式，支持查看服务器端对话记录） |
 | 运维探针 | `GET /healthz`（存活）、`GET /readyz`（就绪） |
 
+OpenAI `/v1/*` 仍是推荐的规范路径；同时支持 `/models`、`/chat/completions`、`/responses`、`/embeddings`、`/files` 等根路径快捷路由，方便只配置 DS2API 根地址的第三方客户端。
+
 ## 平台兼容矩阵
 
 | 级别 | 平台 | 当前状态 |
@@ -134,10 +160,9 @@ flowchart LR
 | expert | `deepseek-v4-pro-search-nothinking` | 永久关闭，不受请求参数影响 | ✅ |
 | vision | `deepseek-v4-vision` | 默认开启，可由请求参数控制 | ❌ |
 | vision | `deepseek-v4-vision-nothinking` | 永久关闭，不受请求参数影响 | ❌ |
-| vision | `deepseek-v4-vision-search` | 默认开启，可由请求参数控制 | ✅ |
-| vision | `deepseek-v4-vision-search-nothinking` | 永久关闭，不受请求参数影响 | ✅ |
 
 除原生模型外，也支持常见 alias 输入（如 `gpt-4.1`、`gpt-5`、`gpt-5-codex`、`o3`、`claude-*`、`gemini-*` 等），但 `/v1/models` 返回的是规范化后的 DeepSeek 原生模型 ID。若 alias 名本身追加 `-nothinking` 后缀，也会映射到对应的强制关思考模型。完整 alias 行为以 [API.md](API.md#模型-alias-解析策略) 和 `config.example.json` 为准。
+当前上游视觉模型只暴露 `vision` 通道，不提供独立的联网搜索视觉变体。
 
 ### Claude 接口（`GET /anthropic/v1/models`）
 
@@ -221,6 +246,7 @@ docker-compose logs -f
 ```
 
 默认 `docker-compose.yml` 会把宿主机 `6011` 映射到容器内的 `5001`。如果你希望直接对外暴露 `5001`，请设置 `DS2API_HOST_PORT=5001`（或者手动调整 `ports` 配置）。
+同时默认把 `./config.json` 挂载到容器 `/data/config.json`，并设置 `DS2API_CONFIG_PATH=/data/config.json`，用于避免 `/app` 只读导致运行时 token 持久化失败。
 
 更新镜像：`docker-compose up -d --build`
 
@@ -291,7 +317,7 @@ go run ./cmd/ds2api
 - `runtime`：账号并发、队列与 token 刷新策略，可通过 Admin Settings 热更新。
 - `auto_delete.mode`：请求结束后的远端会话清理策略，支持 `none` / `single` / `all`。
 - `history_split`：旧轮次拆分字段，已废弃并忽略，仅保留兼容旧配置。
-- `current_input_file`：唯一生效的独立拆分策略；默认开启且阈值为 `0`，触发时将完整上下文合并上传为隐藏上下文文件。
+- `current_input_file`：唯一生效的独立拆分策略；默认开启且阈值为 `0`，触发时将完整上下文合并上传为 `history.txt` 上下文文件。
 - 如果关闭 `current_input_file`，请求会直接透传，不上传拆分上下文文件。
 - `thinking_injection`：默认开启；在最新 user 消息末尾追加思考增强提示词，提高高强度推理与工具调用前的思考稳定性；`prompt` 留空时使用内置默认提示词。
 

README.en.md

@@ -28,6 +28,30 @@ Documentation entry: [Docs Index](docs/README.md) / [Architecture](docs/ARCHITEC
 >
 > Do not use this project in ways that violate service terms, agreements, laws, or platform rules. Before any commercial use, review the `LICENSE`, the relevant terms, and confirm that you have the author's written permission.
 
+## Table of Contents
+
+- [Architecture Overview (Summary)](#architecture-overview-summary)
+- [Key Capabilities](#key-capabilities)
+- [Platform Compatibility Matrix](#platform-compatibility-matrix)
+- [Model Support](#model-support)
+  - [OpenAI Endpoint](#openai-endpoint-get-v1models)
+  - [Claude Endpoint](#claude-endpoint-get-anthropicv1models)
+  - [Gemini Endpoint](#gemini-endpoint)
+- [Quick Start](#quick-start)
+  - [Option 1: Download Release Binaries](#option-1-download-release-binaries)
+  - [Option 2: Docker / GHCR](#option-2-docker--ghcr)
+  - [Option 3: Vercel](#option-3-vercel)
+  - [Option 4: Local Run](#option-4-local-run)
+- [Configuration](#configuration)
+- [Authentication Modes](#authentication-modes)
+- [Concurrency Model](#concurrency-model)
+- [Tool Call Adaptation](#tool-call-adaptation)
+- [Local Dev Packet Capture](#local-dev-packet-capture)
+- [Documentation Index](#documentation-index)
+- [Testing](#testing)
+- [Release Artifact Automation (GitHub Actions)](#release-artifact-automation-github-actions)
+- [Disclaimer](#disclaimer)
+
 ## Architecture Overview (Summary)
 
 ```mermaid
@@ -104,6 +128,8 @@ For the full module-by-module architecture and directory responsibilities, see [
 | WebUI Admin Panel | SPA at `/admin` (bilingual Chinese/English, dark mode, with server-side conversation history) |
 | Health Probes | `GET /healthz` (liveness), `GET /readyz` (readiness) |
 
+OpenAI `/v1/*` routes remain canonical, and DS2API also accepts root shortcuts such as `/models`, `/chat/completions`, `/responses`, `/embeddings`, and `/files` for clients configured with the bare service URL.
+
 ## Platform Compatibility Matrix
 
 | Tier | Platform | Status |
@@ -126,9 +152,9 @@ For the full module-by-module architecture and directory responsibilities, see [
 | default | `deepseek-v4-flash-search` | enabled by default, request-controlled | ✅ |
 | expert | `deepseek-v4-pro-search` | enabled by default, request-controlled | ✅ |
 | vision | `deepseek-v4-vision` | enabled by default, request-controlled | ❌ |
-| vision | `deepseek-v4-vision-search` | enabled by default, request-controlled | ✅ |
 
 Besides native IDs, DS2API also accepts common aliases as input (for example `gpt-4.1`, `gpt-5`, `gpt-5-codex`, `o3`, `claude-*`, `gemini-*`), but `/v1/models` returns normalized DeepSeek native model IDs. The complete alias behavior is documented in [API.en.md](API.en.md#model-alias-resolution) and `config.example.json`.
+Current upstream vision support exposes only the `vision` lane and does not provide a separate search-enabled vision variant.
 
 ### Claude Endpoint (`GET /anthropic/v1/models`)
 
@@ -209,6 +235,7 @@ docker-compose up -d
 ```
 
 The default `docker-compose.yml` uses `ghcr.io/cjackhwang/ds2api:latest` and maps host port `6011` to container port `5001`. If you want `5001` exposed directly, set `DS2API_HOST_PORT=5001` (or adjust the `ports` mapping).
+It also mounts `./config.json` to `/data/config.json` and sets `DS2API_CONFIG_PATH=/data/config.json` by default, which avoids runtime token persistence failures caused by read-only `/app`.
 
 Rebuild after updates: `docker-compose up -d --build`
 
@@ -279,7 +306,7 @@ Common fields:
 - `runtime`: account concurrency, queueing, and token refresh behavior, hot-reloadable via Admin Settings.
 - `auto_delete.mode`: remote session cleanup after each request, supporting `none` / `single` / `all`.
 - `history_split`: legacy multi-turn history split field, now ignored and kept only for backward-compatible config loading.
-- `current_input_file`: the only active split mode; it is enabled by default and uploads the full context as a hidden context file once the character threshold is reached.
+- `current_input_file`: the only active split mode; it is enabled by default and uploads the full context as a `history.txt` context file once the character threshold is reached.
 - If you turn off `current_input_file`, requests pass through directly without uploading any split context file.
 
 For the full environment variable list, see [docs/DEPLOY.en.md](docs/DEPLOY.en.md). For auth behavior, see [API.en.md](API.en.md#authentication).

VERSION

@@ -1 +1 @@
-4.1.2
+4.2.0

cmd/ds2api/main.go

@@ -35,8 +35,9 @@ func main() {
 	}
 
 	srv := &http.Server{
-		Addr:    "0.0.0.0:" + port,
-		Handler: app.Router,
+		Addr:              "0.0.0.0:" + port,
+		Handler:           app.Router,
+		ReadHeaderTimeout: 5 * time.Second,
 	}
 	localURL := fmt.Sprintf("http://127.0.0.1:%s", port)
 	lanIP := detectLANIPv4()

docker-compose.yml

@@ -9,8 +9,9 @@ services:
       # Host port is configurable via DS2API_HOST_PORT; container port stays fixed at 5001.
       - "${DS2API_HOST_PORT:-6011}:5001"
     volumes:
-      - ./config.json:/app/config.json    # 配置文件
+      - ./config.json:/data/config.json   # 配置文件（持久化推荐路径）
     environment:
       - TZ=Asia/Shanghai
       - LOG_LEVEL=INFO
       - DS2API_ADMIN_KEY=${DS2API_ADMIN_KEY:-ds2api}
+      - DS2API_CONFIG_PATH=/data/config.json

docs/DEPLOY.en.md

@@ -130,6 +130,8 @@ docker-compose logs -f
 ```
 
 The default `docker-compose.yml` directly uses `ghcr.io/cjackhwang/ds2api:latest` and maps host port `6011` to container port `5001`. If you want `5001` exposed directly, set `DS2API_HOST_PORT=5001` (or adjust the `ports` mapping).
+The compose template also defaults to `DS2API_CONFIG_PATH=/data/config.json` with `./config.json:/data/config.json` mounted, so deployments avoid read-only `/app` persistence issues by default.
+Compatibility note: when `DS2API_CONFIG_PATH` is unset and runtime base dir is `/app`, newer versions prefer `/data/config.json`; if that file is missing but legacy `/app/config.json` exists, DS2API automatically falls back to the legacy path to avoid post-upgrade config loss.
 
 If you want a pinned version instead of `latest`, you can also pull a specific tag directly:
 
@@ -195,6 +197,11 @@ Notes:
 
 - **Port**: DS2API listens on `5001` by default; the template sets `PORT=5001`.
 - **Persistent config**: the template mounts `/data` and sets `DS2API_CONFIG_PATH=/data/config.json`. After importing config in Admin UI, it will be written and persisted to this path.
+- **`open /app/config.json: permission denied`**: this means the instance is trying to persist runtime tokens to a read-only path (commonly `/app` inside the image).  
+  Recommended handling:
+  1. Set a writable path explicitly: `DS2API_CONFIG_PATH=/data/config.json` (and mount a persistent volume at `/data`);
+  2. If you bootstrap with `DS2API_CONFIG_JSON` and do not need runtime writeback, keep env-backed mode (`DS2API_ENV_WRITEBACK` disabled);
+  3. In current versions, login/session tests continue even if persistence fails; Admin API returns a warning that token persistence failed and token is memory-only until restart.
 - **Build version**: Zeabur / regular `docker build` does not require `BUILD_VERSION` by default. The image prefers that build arg when provided, and automatically falls back to the repo-root `VERSION` file when it is absent.
 - **First login**: after deployment, open `/admin` and login with `DS2API_ADMIN_KEY` shown in Zeabur env/template instructions (recommended: rotate to a strong secret after first login).
 

docs/DEPLOY.md

@@ -130,6 +130,8 @@ docker-compose logs -f
 ```
 
 默认 `docker-compose.yml` 直接使用 `ghcr.io/cjackhwang/ds2api:latest`，并把宿主机 `6011` 映射到容器内的 `5001`。如果你希望直接对外暴露 `5001`，请设置 `DS2API_HOST_PORT=5001`（或者手动调整 `ports` 配置）。
+Compose 模板还会默认设置 `DS2API_CONFIG_PATH=/data/config.json` 并挂载 `./config.json:/data/config.json`，优先避免 `/app` 只读带来的配置持久化问题。
+兼容说明：若未设置 `DS2API_CONFIG_PATH` 且运行目录是 `/app`，新版本会优先使用 `/data/config.json`；当该文件不存在但检测到历史 `/app/config.json` 时，会自动回退读取旧路径，避免升级后“配置丢失”。
 
 如需固定版本，也可以直接拉取指定 tag：
 
@@ -195,6 +197,11 @@ healthcheck:
 
 - **端口**：服务默认监听 `5001`，模板会固定设置 `PORT=5001`。
 - **配置持久化**：模板挂载卷 `/data`，并设置 `DS2API_CONFIG_PATH=/data/config.json`；在管理台导入配置后，会写入并持久化到该路径。
+- **`open /app/config.json: permission denied`**：说明当前实例在尝试把运行时 token 持久化到只读路径（常见于镜像内 `/app`）。  
+  处理建议：
+  1. 显式设置可写路径：`DS2API_CONFIG_PATH=/data/config.json`（并挂载持久卷到 `/data`）；  
+  2. 若你使用 `DS2API_CONFIG_JSON` 启动且不需要运行时落盘，可保持环境变量模式（`DS2API_ENV_WRITEBACK` 关闭）；  
+  3. 最新版本中，即使持久化失败，登录/会话测试仍会继续，仅提示“token 未持久化（重启后丢失）”。
 - **构建版本号**：Zeabur / 普通 `docker build` 默认不需要传 `BUILD_VERSION`；镜像会优先使用该构建参数，未提供时自动回退到仓库根目录的 `VERSION` 文件。
 - **首次登录**：部署完成后访问 `/admin`，使用 Zeabur 环境变量/模板指引中的 `DS2API_ADMIN_KEY` 登录（建议首次登录后自行更换为强密码）。
 

docs/DeepSeekSSE行为结构说明-2026-04-05.md

@@ -309,7 +309,18 @@ parse SSE block
 - 新模型可能增加新的 `p` 路径。
 - 新版本可能增加新的 fragment.type。
 - `CONTENT_FILTER` 的终态模板内容可能变化。
-- 自动续写相关状态（如 `INCOMPLETE` / `AUTO_CONTINUE`）当前主要来自实测与实现兼容逻辑，后续字段形态仍可能变化。
+- 自动续写相关状态（如 `INCOMPLETE` / `AUTO_CONTINUE`）当前主要来自实测与实现兼容逻辑，后续字段形态仍可能变化。当前实现不会仅因早期 `WIP` 状态就自动继续；只有显式 `INCOMPLETE` 或 `auto_continue` 信号才会触发 continue。
 - 解析器应当对未知字段、未知路径、未知事件保持容忍。
 
 如果你要把这份说明用于实际开发，建议同时保留原始流样本、回放脚本和回归测试，不要只依赖本文。
+
+## 2026-04-29 最近线上样本增量观察
+
+基于 `longtext-deepseek-v4-flash-20260429` 与 `longtext-deepseek-v4-pro-20260429` 两个真实账号长文本样本，近期格式变化要点如下：
+
+1. `data:` 事件中仍大量出现 `{"v":"..."}` 的无路径增量（`p` 缺失），解析器必须把空路径视为可见正文候选，而不能只依赖 `response/content`。
+2. 对象形态 `v`（如 `{"text":"..."}` / `{"content":"..."}`）仍会出现，且可能与无路径 chunk 混用；仅按字符串处理会导致正文丢块。
+3. 多轮 continuation 场景下，后续 chunk 可能不再重复显式 `status`，状态机需要保留上一轮 `INCOMPLETE` 语义直到出现终态。
+4. 2026-04-29 起客户端头部版本基线上调到 `x-client-version: 2.0.3`，否则部分账号会出现上游行为不一致（包括空输出与补轮异常）。
+
+建议：新增样本默认回放应优先覆盖「长文本 + 多轮 + 无路径 chunk」组合，避免只用短样本导致回归漏检。

docs/prompt-compatibility.md

@@ -98,13 +98,16 @@ DS2API 当前的核心思路，不是把客户端传来的 `messages`、`tools`
 - `prompt` 才是对话上下文主载体。
 - `ref_file_ids` 只承载文件引用，不承载普通文本消息。
 - `tools` 不会作为“原生工具 schema”直接下发给下游，而是被改写进 `prompt`。
+- 对外返回给客户端的 `prompt_tokens` / `input_tokens` / `promptTokenCount` 不再按“最后一条消息”或字符粗估近似返回，而是基于**完整上下文 prompt**做 tokenizer 计数；为了避免上下文实际超限但客户端误以为还能塞下，请求侧上下文 token 会额外保守上浮一点，宁可略大也不低估。
 - 当前 `/v1/chat/completions` 业务路径仍是“每次请求新建一个远端 `chat_session_id`，并默认发送 `parent_message_id: null`”；因此 DS2API 对外默认表现为“新会话 + prompt 拼历史”，而不是复用 DeepSeek 原生会话树。
 - 但 DeepSeek 远端本身支持同一 `chat_session_id` 的跨轮次持续对话。2026-04-27 已用项目内现有 DeepSeek client 做过一次不改业务代码的双轮实测：同一 `chat_session_id` 下，第 1 轮返回 `request_message_id=1` / `response_message_id=2` / 文本 `SESSION_TEST_ONE`；第 2 轮重新获取一次 PoW，并发送 `parent_message_id=2` 后，成功返回 `request_message_id=3` / `response_message_id=4` / 文本 `SESSION_TEST_TWO`。这说明“同远端会话持续聊天”能力存在，且每轮需要携带正确的 parent/message 链接信息，同时重新获取对应轮次可用的 PoW。
 - OpenAI Chat / Responses 原生走统一 OpenAI 标准化与 DeepSeek payload 组装；Claude / Gemini 会尽量复用 OpenAI prompt/tool 语义，其中 Gemini 直接复用 `promptcompat.BuildOpenAIPromptForAdapter`，Claude 消息接口在可代理场景会转换为 OpenAI chat 形态再执行。
 - 客户端传入的 thinking / reasoning 开关会被归一到下游 `thinking_enabled`。Gemini `generationConfig.thinkingConfig.thinkingBudget` 会翻译成同一套 thinking 开关；关闭时即使上游返回 `response/thinking_content`，兼容层也不会把它当作可见正文输出。若最终解析出的模型名带 `-nothinking` 后缀，则会无条件强制关闭 thinking，优先级高于请求体中的 `thinking` / `reasoning` / `reasoning_effort`。Claude surface 在流式请求且未显式声明 `thinking` 时，仍按 Anthropic 语义默认关闭；但在非流式代理场景，兼容层会内部开启一次下游 thinking，用于捕获“正文为空、工具调用落在 thinking 里”的情况，随后在回包前剥离用户不可见的 thinking block。
-- 对 OpenAI Chat / Responses 的非流式收尾，如果最终可见正文为空，兼容层会优先尝试把思维链中的独立 DSML / XML 工具块当作真实工具调用解析出来。流式链路也会在收尾阶段做同样的 fallback 检测，但不会因为思维链内容去中途拦截或改写流式输出；thinking / reasoning 增量仍按原样先发，只有在结束收尾时才可能补发最终工具调用结果。补发结果会作为本轮 assistant 的结构化 `tool_calls` / `function_call` 输出返回，而不是塞进 `content` 文本；如果客户端没有开启 thinking / reasoning，思维链只用于检测，不会作为 `reasoning_content` 或可见正文暴露。只有正文为空且思维链里也没有可执行工具调用时，才继续按空回复错误处理。
+- 对 OpenAI Chat / Responses 的非流式收尾，如果最终可见正文为空，兼容层会优先尝试把思维链中的独立 DSML / XML 工具块当作真实工具调用解析出来。流式链路也会在收尾阶段做同样的 fallback 检测，但不会因为思维链内容去中途拦截或改写流式输出；真正的工具识别始终基于原始上游文本，而不是基于“已经做过可见输出清洗”的版本，因此即使最终可见层会剥离完整 leaked DSML / XML `tool_calls` wrapper、并抑制全空参数或无效 wrapper 块，也不会影响真实工具调用转成结构化 `tool_calls` / `function_call`。补发结果会作为本轮 assistant 的结构化 `tool_calls` / `function_call` 输出返回，而不是塞进 `content` 文本；如果客户端没有开启 thinking / reasoning，思维链只用于检测，不会作为 `reasoning_content` 或可见正文暴露。只有正文为空且思维链里也没有可执行工具调用时，才继续按空回复错误处理。
 - OpenAI Chat / Responses 的空回复错误处理之前会默认做一次内部补偿重试：第一次上游完整结束后，如果最终可见正文为空、没有解析到工具调用、也没有已经向客户端流式发出工具调用，并且终止原因不是 `content_filter`，兼容层会复用同一个 `chat_session_id`、账号、token 与工具策略，把原始 completion `prompt` 追加固定后缀 `Previous reply had no visible output. Please regenerate the visible final answer or tool call now.` 后重新提交一次。重试遵循 DeepSeek 多轮对话协议：从第一次上游 SSE 流中提取 `response_message_id`，并在重试 payload 中设置 `parent_message_id` 为该值，使重试成为同一会话的后续轮次而非断裂的根消息；同时重新获取一次 PoW（若 PoW 获取失败则回退到原始 PoW）。该重试不会重新标准化消息、不会新建 session、不会切换账号，也不会向流式客户端插入重试标记；第二次 thinking / reasoning 会按正常增量直接接到第一次之后，并继续使用 overlap trim 去重。若第二次仍为空，终端错误码仍保持现有 `upstream_empty_output`；若任一尝试触发空 `content_filter`，不做补偿重试并保持 `content_filter` 错误。JS Vercel 运行时同样设置 `parent_message_id`，但因无法直接调用 PoW API 而复用原始 PoW。
 
+- OpenAI Chat / Responses 在最终可见正文渲染阶段，会把 DeepSeek 搜索返回中的 `[citation:N]` / `[reference:N]` 标记替换成对应 Markdown 链接。`citation` 标记按一基序号解析；`reference` 标记只有在同一段正文中出现 `[reference:0]`（允许冒号后有空格）时才按零基序号映射，并且不会影响同段正文里的 `citation` 标记。
+
 ## 5. prompt 是怎么拼出来的
 
 OpenAI Chat / Responses 在标准化后、current input file 之前，会默认执行 `thinking_injection` 增强。它参考 DeepSeek V4 “把控制指令放在 user 消息末尾更稳定”的用法，在最新 user message 后追加思考增强提示词。当前内置默认提示词以 `Reasoning Effort: Absolute maximum with no shortcuts permitted.` 开头，并继续要求模型充分分解问题、覆盖潜在路径与边界条件、把完整推演过程显式写出。该开关默认启用，可通过 `thinking_injection.enabled=false` 关闭；也可以通过 `thinking_injection.prompt` 自定义提示词，留空时使用内置默认提示词。
@@ -154,6 +157,7 @@ OpenAI Chat / Responses 在标准化后、current input file 之前，会默认
 兼容层仍接受旧式纯 `<tool_calls>` wrapper，但提示词会优先要求模型输出官方 DSML 标签，并强调不能只输出 closing wrapper 而漏掉 opening tag。需要注意：这是“兼容 DSML 外壳，内部仍以 XML 解析语义为准”，不是原生 DSML 全链路实现；DSML 标签会在解析入口归一化回现有 XML 标签后继续走同一套 parser。
 数组参数使用 `<item>...</item>` 子节点表示；当某个参数体只包含 item 子节点时，Go / Node 解析器会把它还原成数组，避免 `questions` / `options` 这类 schema 中要求 array 的参数被误解析成 `{ "item": ... }` 对象。若模型把完整结构化 XML fragment 误包进 CDATA，兼容层会在保护 `content` / `command` 等原文字段的前提下，尝试把非原文字段中的 CDATA XML fragment 还原成 object / array。不过，如果 CDATA 只是单个平面的 XML/HTML 标签，例如 `<b>urgent</b>` 这种行内标记，兼容层会保留原始字符串，不会强行升成 object / array；只有明显表示结构的 CDATA 片段，例如多兄弟节点、嵌套子节点或 `item` 列表，才会触发结构化恢复。
 在 assistant 最终回包阶段，如果某个 tool 参数在声明 schema 中明确是 `string`，兼容层会在把解析后的 `tool_calls` / `function_call` 重新序列化成 OpenAI / Responses / Claude 可见参数前，递归把该路径上的 number / bool / object / array 统一转成字符串；其中 object / array 会压成紧凑 JSON 字符串。这个保护只对 schema 明确声明为 string 的路径生效，不会改写本来就是 `number` / `boolean` / `object` / `array` 的参数。这样可以兼容 DeepSeek 输出了结构化片段、但上游客户端工具 schema 又严格要求字符串参数的场景（例如 `content`、`prompt`、`path`、`taskId` 等）。
+工具 schema 的权威来源始终是**当前请求实际携带的 schema**，而不是同名工具在其他 runtime（Claude Code / OpenCode / Codex 等）里的默认印象。兼容层现在会同时兼容 OpenAI 风格 `function.parameters`、直接工具对象上的 `parameters` / `input_schema`、以及 camelCase 的 `inputSchema` / `schema`，并在最终输出阶段按这份请求内 schema 决定是保留 array/object，还是仅对明确声明为 `string` 的路径做字符串化。该规则同样适用于 Claude 的流式收尾和 Vercel Node 流式 tool-call formatter，避免不同 runtime 因 schema shape 差异而出现同名工具参数类型漂移。
 正例中的工具名只会来自当前请求实际声明的工具；如果当前请求没有足够的已知工具形态，就省略对应的单工具、多工具或嵌套示例，避免把不可用工具名写进 prompt。
 对执行类工具，脚本内容必须进入执行参数本身：`Bash` / `execute_command` 使用 `command`，`exec_command` 使用 `cmd`；不要把脚本示范成 `path` / `content` 文件写入参数。
 
@@ -243,9 +247,10 @@ OpenAI 文件相关实现：
 
 兼容层现在只保留 `current_input_file` 这一种拆分方式；旧的 `history_split` 已废弃，只保留为兼容旧配置的字段，不再参与请求处理。
 
-- `current_input_file` 默认开启；它用于把“完整上下文”合并进隐藏上下文文件。当最新 user turn 的纯文本长度达到 `current_input_file.min_chars`（默认 `0`）时，兼容层会上传一个文件名为 `IGNORE.txt` 的上下文文件，并在 live prompt 中只保留一个中性的 user 消息要求模型直接回答最新请求，不再暴露文件名或要求模型读取本地文件。
+- `current_input_file` 默认开启；它用于把“完整上下文”合并进 `history.txt` 上下文文件。当最新 user turn 的纯文本长度达到 `current_input_file.min_chars`（默认 `0`）时，兼容层会上传一个文件名为 `history.txt` 的上下文文件，并在 live prompt 中只保留一个中性的 user 消息要求模型直接回答最新请求，不再暴露文件名或要求模型读取本地文件。
 - 如果 `current_input_file.enabled=false`，请求会直接透传，不上传任何拆分上下文文件。
 - 旧的 `history_split.enabled` / `history_split.trigger_after_turns` 会被读取进配置对象以保持兼容，但不会触发拆分上传，也不会影响 `current_input_file` 的默认开启。
+- 即使触发 `current_input_file` 后 live prompt 被缩短，对客户端回包里的上下文 token 统计，仍会沿用**拆分前的完整 prompt 语义**做计数，而不是按缩短后的占位 prompt 计算；否则会把真实上下文显著算小。
 
 相关实现：
 
@@ -256,16 +261,11 @@ OpenAI 文件相关实现：
 - 旧历史拆分兼容壳：
   [internal/httpapi/openai/history/history_split.go](../internal/httpapi/openai/history/history_split.go)
 
-当前输入转文件启用并触发时，上传文件的真实文件名是 `IGNORE.txt`，文件内容是完整 `messages` 上下文；它仍会先用 OpenAI 消息标准化和 DeepSeek 角色标记序列化，再包进 `IGNORE` 文件边界里：
+当前输入转文件启用并触发时，上传文件的真实文件名是 `history.txt`，文件内容是完整 `messages` 上下文；它仍会先用 OpenAI 消息标准化和 DeepSeek 角色标记序列化，并直接作为 `history.txt` 的纯文本内容上传（不再注入文件边界标签）：
 
 ```text
-[uploaded filename]: IGNORE.txt
-[file content end]
-
+[uploaded filename]: history.txt
 <｜begin▁of▁sentence｜><｜System｜>...<｜User｜>...<｜Assistant｜>...<｜Tool｜>...<｜User｜>...
-
-[file name]: IGNORE
-[file content begin]
 ```
 
 开启后，请求的 live prompt 不再直接内联完整上下文，而是保留一个 user role 的短提示，提示模型基于已提供上下文直接回答最新请求；上传后的 `file_id` 会进入 `ref_file_ids`。
@@ -332,7 +332,7 @@ OpenAI 文件相关实现：
 
 - 大部分结构化语义被压进 `prompt`
 - 文件保持文件
-- 需要时把完整上下文拆进隐藏上下文文件
+- 需要时把完整上下文拆进 `history.txt` 上下文文件
 
 ## 12. 修改时必须同步本文档的场景
 
@@ -345,7 +345,7 @@ OpenAI 文件相关实现：
 - tool result 注入方式变更
 - tool prompt 模板或 tool_choice 约束变更
 - inline 文件上传 / 文件引用收集规则变更
-- current input file 触发条件、上传格式、`IGNORE` 包装格式变更
+- current input file 触发条件、上传格式、`history.txt` 包装格式变更
 - 旧 `history_split` 兼容逻辑的读取、忽略或退化行为变更
 - completion payload 字段语义变更
 - Claude / Gemini 对这套统一语义的复用关系变更

go.mod

@@ -10,6 +10,11 @@ require (
 	github.com/router-for-me/CLIProxyAPI/v6 v6.9.14
 )
 
+require (
+	github.com/dlclark/regexp2 v1.11.5 // indirect
+	github.com/hupe1980/go-tiktoken v0.0.10 // indirect
+)
+
 require (
 	github.com/klauspost/compress v1.18.5 // indirect
 	github.com/sirupsen/logrus v1.9.4 // indirect

go.sum

@@ -2,10 +2,14 @@ github.com/andybalholm/brotli v1.2.1 h1:R+f5xP285VArJDRgowrfb9DqL18yVK0gKAW/F+eT
 github.com/andybalholm/brotli v1.2.1/go.mod h1:rzTDkvFWvIrjDXZHkuS16NPggd91W3kUSvPlQ1pLaKY=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dlclark/regexp2 v1.11.5 h1:Q/sSnsKerHeCkc/jSTNq1oCm7KiVgUMZRDUoRu0JQZQ=
+github.com/dlclark/regexp2 v1.11.5/go.mod h1:DHkYz0B9wPfa6wondMfaivmHpzrQ3v9q8cnmRbL6yW8=
 github.com/go-chi/chi/v5 v5.2.5 h1:Eg4myHZBjyvJmAFjFvWgrqDTXFyOzjj7YIm3L3mu6Ug=
 github.com/go-chi/chi/v5 v5.2.5/go.mod h1:X7Gx4mteadT3eDOMTsXzmI4/rwUpOwBHLpAfupzFJP0=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/hupe1980/go-tiktoken v0.0.10 h1:m6phOJaGyctqWdGIgwn9X8AfJvaG74tnQoDL+ntOUEQ=
+github.com/hupe1980/go-tiktoken v0.0.10/go.mod h1:NME6d8hrE+Jo+kLUZHhXShYV8e40hYkm4BbSLQKtvAo=
 github.com/klauspost/compress v1.18.5 h1:/h1gH5Ce+VWNLSWqPzOVn6XBO+vJbCNGvjoaGBFW2IE=
 github.com/klauspost/compress v1.18.5/go.mod h1:cwPg85FWrGar70rWktvGQj8/hthj3wpl0PGDogxkrSQ=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=

internal/chathistory/store.go

@@ -14,6 +14,7 @@ import (
 	"github.com/google/uuid"
 
 	"ds2api/internal/config"
+	"ds2api/internal/util"
 )
 
 const (
@@ -610,8 +611,8 @@ func buildPreview(item Entry) string {
 	if candidate == "" {
 		candidate = strings.TrimSpace(item.UserInput)
 	}
-	if len(candidate) > defaultPreviewAt {
-		return candidate[:defaultPreviewAt] + "..."
+	if truncated, ok := util.TruncateRunes(candidate, defaultPreviewAt); ok {
+		return truncated + "..."
 	}
 	return candidate
 }

internal/chathistory/store_test.go

@@ -8,6 +8,7 @@ import (
 	"strings"
 	"sync"
 	"testing"
+	"unicode/utf8"
 )
 
 func blockDetailDir(t *testing.T, detailDir string) func() {
@@ -105,6 +106,17 @@ func TestStoreCreatesAndPersistsEntries(t *testing.T) {
 	}
 }
 
+func TestBuildPreviewPreservesUTF8MB4Characters(t *testing.T) {
+	long := strings.Repeat("😀", defaultPreviewAt+1)
+	preview := buildPreview(Entry{Content: long})
+	if !utf8.ValidString(preview) {
+		t.Fatalf("expected valid utf-8 preview, got %q", preview)
+	}
+	if preview != strings.Repeat("😀", defaultPreviewAt)+"..." {
+		t.Fatalf("unexpected preview: %q", preview)
+	}
+}
+
 func TestStoreTrimsToConfiguredLimit(t *testing.T) {
 	path := filepath.Join(t.TempDir(), "chat_history.json")
 	store := New(path)

internal/config/config_edge_test.go

@@ -79,13 +79,20 @@ func TestGetModelConfigDeepSeekExpertReasonerSearch(t *testing.T) {
 	}
 }
 
-func TestGetModelConfigDeepSeekVisionReasonerSearch(t *testing.T) {
-	thinking, search, ok := GetModelConfig("deepseek-v4-vision-search")
+func TestGetModelConfigDeepSeekVision(t *testing.T) {
+	thinking, search, ok := GetModelConfig("deepseek-v4-vision")
 	if !ok {
-		t.Fatal("expected ok for deepseek-v4-vision-search")
+		t.Fatal("expected ok for deepseek-v4-vision")
 	}
-	if !thinking || !search {
-		t.Fatalf("expected both true, got thinking=%v search=%v", thinking, search)
+	if !thinking || search {
+		t.Fatalf("expected thinking=true search=false, got thinking=%v search=%v", thinking, search)
+	}
+}
+
+func TestGetModelConfigDeepSeekVisionSearchUnsupported(t *testing.T) {
+	_, _, ok := GetModelConfig("deepseek-v4-vision-search")
+	if ok {
+		t.Fatal("expected deepseek-v4-vision-search to be unsupported")
 	}
 }
 
@@ -748,18 +755,16 @@ func TestOpenAIModelsResponse(t *testing.T) {
 		t.Fatal("expected non-empty models list")
 	}
 	expected := map[string]bool{
-		"deepseek-v4-flash":                    false,
-		"deepseek-v4-flash-nothinking":         false,
-		"deepseek-v4-pro":                      false,
-		"deepseek-v4-pro-nothinking":           false,
-		"deepseek-v4-flash-search":             false,
-		"deepseek-v4-flash-search-nothinking":  false,
-		"deepseek-v4-pro-search":               false,
-		"deepseek-v4-pro-search-nothinking":    false,
-		"deepseek-v4-vision":                   false,
-		"deepseek-v4-vision-nothinking":        false,
-		"deepseek-v4-vision-search":            false,
-		"deepseek-v4-vision-search-nothinking": false,
+		"deepseek-v4-flash":                   false,
+		"deepseek-v4-flash-nothinking":        false,
+		"deepseek-v4-pro":                     false,
+		"deepseek-v4-pro-nothinking":          false,
+		"deepseek-v4-flash-search":            false,
+		"deepseek-v4-flash-search-nothinking": false,
+		"deepseek-v4-pro-search":              false,
+		"deepseek-v4-pro-search-nothinking":   false,
+		"deepseek-v4-vision":                  false,
+		"deepseek-v4-vision-nothinking":       false,
 	}
 	for _, model := range data {
 		if _, ok := expected[model.ID]; ok {

internal/config/model_alias_test.go

@@ -144,10 +144,17 @@ func TestResolveModelCustomAliasToExpert(t *testing.T) {
 
 func TestResolveModelCustomAliasToVision(t *testing.T) {
 	got, ok := ResolveModel(mockModelAliasReader{
-		"my-vision-model": "deepseek-v4-vision-search",
+		"my-vision-model": "deepseek-v4-vision",
 	}, "my-vision-model")
-	if !ok || got != "deepseek-v4-vision-search" {
-		t.Fatalf("expected alias -> deepseek-v4-vision-search, got ok=%v model=%q", ok, got)
+	if !ok || got != "deepseek-v4-vision" {
+		t.Fatalf("expected alias -> deepseek-v4-vision, got ok=%v model=%q", ok, got)
+	}
+}
+
+func TestResolveModelHeuristicVisionIgnoresSearchSuffix(t *testing.T) {
+	got, ok := ResolveModel(nil, "gemini-vision-search")
+	if !ok || got != "deepseek-v4-vision" {
+		t.Fatalf("expected heuristic vision alias to resolve without search variant, got ok=%v model=%q", ok, got)
 	}
 }
 

internal/config/models.go

@@ -22,7 +22,6 @@ var deepSeekBaseModels = []ModelInfo{
 	{ID: "deepseek-v4-flash-search", Object: "model", Created: 1677610602, OwnedBy: "deepseek", Permission: []any{}},
 	{ID: "deepseek-v4-pro-search", Object: "model", Created: 1677610602, OwnedBy: "deepseek", Permission: []any{}},
 	{ID: "deepseek-v4-vision", Object: "model", Created: 1677610602, OwnedBy: "deepseek", Permission: []any{}},
-	{ID: "deepseek-v4-vision-search", Object: "model", Created: 1677610602, OwnedBy: "deepseek", Permission: []any{}},
 }
 
 var DeepSeekModels = appendNoThinkingVariants(deepSeekBaseModels)
@@ -67,7 +66,7 @@ func GetModelConfig(model string) (thinking bool, search bool, ok bool) {
 	switch baseModel {
 	case "deepseek-v4-flash", "deepseek-v4-pro", "deepseek-v4-vision":
 		return !noThinking, false, true
-	case "deepseek-v4-flash-search", "deepseek-v4-pro-search", "deepseek-v4-vision-search":
+	case "deepseek-v4-flash-search", "deepseek-v4-pro-search":
 		return !noThinking, true, true
 	default:
 		return false, false, false
@@ -81,7 +80,7 @@ func GetModelType(model string) (modelType string, ok bool) {
 		return "default", true
 	case "deepseek-v4-pro", "deepseek-v4-pro-search":
 		return "expert", true
-	case "deepseek-v4-vision", "deepseek-v4-vision-search":
+	case "deepseek-v4-vision":
 		return "vision", true
 	default:
 		return "", false
@@ -359,8 +358,6 @@ func resolveCanonicalModel(aliases map[string]string, model string) (string, boo
 	useSearch := strings.Contains(model, "search")
 
 	switch {
-	case useVision && useSearch:
-		return "deepseek-v4-vision-search", true
 	case useVision:
 		return "deepseek-v4-vision", true
 	case useReasoner && useSearch:

internal/config/paths.go

@@ -30,9 +30,29 @@ func ResolvePath(envKey, defaultRel string) string {
 }
 
 func ConfigPath() string {
+	if strings.TrimSpace(os.Getenv("DS2API_CONFIG_PATH")) == "" && BaseDir() == "/app" {
+		return containerDefaultConfigPath()
+	}
 	return ResolvePath("DS2API_CONFIG_PATH", "config.json")
 }
 
+func containerDefaultConfigPath() string {
+	// Container images run as non-root by default. Only use /data when mounted/provisioned.
+	// Otherwise keep /app/config.json so admin-side save does not fail on MkdirAll("/data").
+	if st, err := os.Stat("/data"); err == nil && st.IsDir() {
+		return "/data/config.json"
+	}
+	return "/app/config.json"
+}
+
+func legacyContainerConfigPath() string {
+	return "/app/config.json"
+}
+
+func shouldTryLegacyContainerConfigPath() bool {
+	return strings.TrimSpace(os.Getenv("DS2API_CONFIG_PATH")) == "" && BaseDir() == "/app"
+}
+
 func RawStreamSampleRoot() string {
 	return ResolvePath("DS2API_RAW_STREAM_SAMPLE_ROOT", "tests/raw_stream_samples")
 }

internal/config/paths_test.go

@@ -0,0 +1,28 @@
+package config
+
+import (
+	"os"
+	"testing"
+)
+
+func TestContainerDefaultConfigPath(t *testing.T) {
+	t.Run("fallback to /app when /data is missing", func(t *testing.T) {
+		// This test environment does not guarantee a writable/mounted /data.
+		// If /data is absent we must keep /app fallback to avoid persistence failures.
+		if _, err := os.Stat("/data"); err == nil {
+			t.Skip("/data exists in this environment; cannot validate missing-/data fallback")
+		}
+		if got := containerDefaultConfigPath(); got != "/app/config.json" {
+			t.Fatalf("containerDefaultConfigPath() = %q, want %q", got, "/app/config.json")
+		}
+	})
+
+	t.Run("prefer /data when /data directory exists", func(t *testing.T) {
+		if _, err := os.Stat("/data"); err != nil {
+			t.Skip("/data does not exist in this environment")
+		}
+		if got := containerDefaultConfigPath(); got != "/data/config.json" {
+			t.Fatalf("containerDefaultConfigPath() = %q, want %q", got, "/data/config.json")
+		}
+	})
+}

internal/config/store.go

@@ -87,12 +87,17 @@ func loadConfig() (Config, bool, error) {
 		}
 		return cfg, true, err
 	}
-
 	cfg, err := loadConfigFromFile(ConfigPath())
 	if err != nil {
+		if shouldTryLegacyContainerConfigPath() {
+			legacyPath := legacyContainerConfigPath()
+			if legacyCfg, legacyErr := loadConfigFromFile(legacyPath); legacyErr == nil {
+				Logger.Info("[config] loaded legacy container config path", "path", legacyPath)
+				return legacyCfg, false, nil
+			}
+		}
 		if IsVercel() {
-			// Vercel one-click deploy may start without a writable/present config file.
-			// Keep an in-memory config so users can bootstrap via WebUI then sync env.
+			// Vercel may start without writable/present config; keep in-memory bootstrap config.
 			return Config{}, true, nil
 		}
 		return Config{}, false, err

internal/deepseek/client/client_continue.go

@@ -7,6 +7,7 @@ import (
 	dsprotocol "ds2api/internal/deepseek/protocol"
 	"encoding/json"
 	"errors"
+	"fmt"
 	"io"
 	"net/http"
 	"strings"
@@ -27,7 +28,7 @@ type continueState struct {
 }
 
 // wrapCompletionWithAutoContinue wraps the completion response body so that
-// if the upstream indicates the response is incomplete (WIP / INCOMPLETE /
+// if the upstream indicates the response is incomplete (INCOMPLETE /
 // AUTO_CONTINUE), ds2api will automatically call the DeepSeek continue
 // endpoint and splice the continuation SSE stream onto the original.
 // The caller sees a single, seamless SSE stream.
@@ -176,12 +177,12 @@ func (s *continueState) observe(data string) {
 	}
 	// Path-based status: {"p": "response/status", "v": "FINISHED"}
 	if p, _ := chunk["p"].(string); p == "response/status" {
-		if status, _ := chunk["v"].(string); status != "" {
-			s.lastStatus = strings.TrimSpace(status)
-			if strings.EqualFold(s.lastStatus, "FINISHED") {
-				s.finished = true
-			}
-		}
+		s.setStatus(asString(chunk["v"]))
+	}
+	if p, _ := chunk["p"].(string); p == "response" {
+		s.observeBatchPatches("response", chunk["v"])
+	} else {
+		s.observeBatchPatches("", chunk["v"])
 	}
 	// Nested v.response
 	v, _ := chunk["v"].(map[string]any)
@@ -189,12 +190,7 @@ func (s *continueState) observe(data string) {
 		if id := intFrom(response["message_id"]); id > 0 {
 			s.responseMessageID = id
 		}
-		if status, _ := response["status"].(string); status != "" {
-			s.lastStatus = strings.TrimSpace(status)
-			if strings.EqualFold(s.lastStatus, "FINISHED") {
-				s.finished = true
-			}
-		}
+		s.setStatus(asString(response["status"]))
 		if autoContinue, ok := response["auto_continue"].(bool); ok && autoContinue {
 			s.lastStatus = "AUTO_CONTINUE"
 		}
@@ -205,18 +201,56 @@ func (s *continueState) observe(data string) {
 			if id := intFrom(response["message_id"]); id > 0 {
 				s.responseMessageID = id
 			}
-			if status, _ := response["status"].(string); status != "" {
-				s.lastStatus = strings.TrimSpace(status)
-				if strings.EqualFold(s.lastStatus, "FINISHED") {
-					s.finished = true
-				}
-			}
+			s.setStatus(asString(response["status"]))
 		}
 	}
 }
 
-// shouldContinue returns true when the upstream indicates the response is
-// not yet finished and we have enough information to issue a continue request.
+func (s *continueState) observeBatchPatches(parentPath string, raw any) {
+	if s == nil {
+		return
+	}
+	patches, ok := raw.([]any)
+	if !ok {
+		return
+	}
+	for _, patch := range patches {
+		m, ok := patch.(map[string]any)
+		if !ok {
+			continue
+		}
+		path := strings.TrimSpace(asString(m["p"]))
+		if path == "" {
+			continue
+		}
+		fullPath := path
+		if parent := strings.Trim(strings.TrimSpace(parentPath), "/"); parent != "" && !strings.Contains(path, "/") {
+			fullPath = parent + "/" + path
+		}
+		switch strings.Trim(strings.TrimSpace(fullPath), "/") {
+		case "response/status", "status", "response/quasi_status", "quasi_status":
+			s.setStatus(asString(m["v"]))
+		}
+	}
+}
+
+func (s *continueState) setStatus(status string) {
+	if s == nil {
+		return
+	}
+	normalized := strings.TrimSpace(status)
+	if normalized == "" {
+		return
+	}
+	s.lastStatus = normalized
+	if strings.EqualFold(normalized, "FINISHED") || strings.EqualFold(normalized, "CONTENT_FILTER") {
+		s.finished = true
+	}
+}
+
+// shouldContinue returns true when the upstream explicitly indicates the
+// response is incomplete and we have enough information to issue a continue
+// request. Plain WIP is not sufficient because normal streams begin in WIP.
 func (s *continueState) shouldContinue() bool {
 	if s == nil {
 		return false
@@ -225,7 +259,7 @@ func (s *continueState) shouldContinue() bool {
 		return false
 	}
 	switch strings.ToUpper(strings.TrimSpace(s.lastStatus)) {
-	case "WIP", "INCOMPLETE", "AUTO_CONTINUE":
+	case "INCOMPLETE", "AUTO_CONTINUE":
 		return true
 	default:
 		return false
@@ -241,3 +275,19 @@ func (s *continueState) prepareForNextRound() {
 	s.finished = false
 	s.lastStatus = ""
 }
+
+func asString(v any) string {
+	if v == nil {
+		return ""
+	}
+	switch x := v.(type) {
+	case string:
+		return x
+	default:
+		s := strings.TrimSpace(strings.ReplaceAll(strings.TrimSpace(fmt.Sprint(v)), "\u0000", ""))
+		if s == "<nil>" {
+			return ""
+		}
+		return s
+	}
+}

internal/deepseek/client/client_continue_test.go

@@ -8,6 +8,7 @@ import (
 	"io"
 	"net/http"
 	"strings"
+	"sync/atomic"
 	"testing"
 
 	"ds2api/internal/auth"
@@ -124,6 +125,90 @@ func TestCallCompletionAutoContinueThreadsPowHeader(t *testing.T) {
 	}
 }
 
+func TestAutoContinueDoesNotTriggerOnPlainWIPWithoutExplicitContinuationSignal(t *testing.T) {
+	initialBody := strings.Join([]string{
+		`data: {"response_message_id":321,"v":{"response":{"message_id":321,"status":"WIP","auto_continue":false}}}`,
+		`data: [DONE]`,
+	}, "\n") + "\n"
+
+	var continueCalls atomic.Int32
+	body := newAutoContinueBody(context.Background(), io.NopCloser(strings.NewReader(initialBody)), "session-123", 8, func(context.Context, string, int) (*http.Response, error) {
+		continueCalls.Add(1)
+		return nil, errors.New("continue should not have been called")
+	})
+	defer func() { _ = body.Close() }()
+
+	out, err := io.ReadAll(body)
+	if err != nil {
+		t.Fatalf("read body failed: %v", err)
+	}
+	if continueCalls.Load() != 0 {
+		t.Fatalf("expected no continue calls, got %d", continueCalls.Load())
+	}
+	if !bytes.Contains(out, []byte(`"status":"WIP"`)) || !bytes.Contains(out, []byte(`data: [DONE]`)) {
+		t.Fatalf("expected original body to pass through unchanged, got=%s", string(out))
+	}
+}
+
+func TestAutoContinueTriggersOnResponseBatchQuasiStatusIncomplete(t *testing.T) {
+	initialBody := strings.Join([]string{
+		`data: {"response_message_id":321,"v":{"response":{"message_id":321,"status":"WIP","auto_continue":false}}}`,
+		`data: {"p":"response","o":"BATCH","v":[{"p":"accumulated_token_usage","v":2413},{"p":"quasi_status","v":"INCOMPLETE"}]}`,
+		`data: [DONE]`,
+	}, "\n") + "\n"
+
+	var continueCalls atomic.Int32
+	body := newAutoContinueBody(context.Background(), io.NopCloser(strings.NewReader(initialBody)), "session-123", 8, func(context.Context, string, int) (*http.Response, error) {
+		continueCalls.Add(1)
+		return &http.Response{
+			StatusCode: http.StatusOK,
+			Header:     make(http.Header),
+			Body: io.NopCloser(strings.NewReader(
+				`data: {"response_message_id":322,"p":"response/status","v":"FINISHED"}` + "\n" +
+					`data: [DONE]` + "\n",
+			)),
+		}, nil
+	})
+	defer func() { _ = body.Close() }()
+
+	out, err := io.ReadAll(body)
+	if err != nil {
+		t.Fatalf("read body failed: %v", err)
+	}
+	if continueCalls.Load() != 1 {
+		t.Fatalf("expected exactly one continue call, got %d", continueCalls.Load())
+	}
+	if !bytes.Contains(out, []byte(`"quasi_status","v":"INCOMPLETE"`)) || !bytes.Contains(out, []byte(`"v":"FINISHED"`)) {
+		t.Fatalf("expected continued output to include initial and final rounds, got=%s", string(out))
+	}
+}
+
+func TestAutoContinueDoesNotTriggerWhenResponseBatchQuasiStatusFinished(t *testing.T) {
+	initialBody := strings.Join([]string{
+		`data: {"response_message_id":321,"v":{"response":{"message_id":321,"status":"WIP","auto_continue":false}}}`,
+		`data: {"p":"response","o":"BATCH","v":[{"p":"accumulated_token_usage","v":2413},{"p":"quasi_status","v":"FINISHED"}]}`,
+		`data: [DONE]`,
+	}, "\n") + "\n"
+
+	var continueCalls atomic.Int32
+	body := newAutoContinueBody(context.Background(), io.NopCloser(strings.NewReader(initialBody)), "session-123", 8, func(context.Context, string, int) (*http.Response, error) {
+		continueCalls.Add(1)
+		return nil, errors.New("continue should not have been called")
+	})
+	defer func() { _ = body.Close() }()
+
+	out, err := io.ReadAll(body)
+	if err != nil {
+		t.Fatalf("read body failed: %v", err)
+	}
+	if continueCalls.Load() != 0 {
+		t.Fatalf("expected no continue calls, got %d", continueCalls.Load())
+	}
+	if !bytes.Contains(out, []byte(`"quasi_status","v":"FINISHED"`)) || !bytes.Contains(out, []byte(`data: [DONE]`)) {
+		t.Fatalf("expected original finished body to pass through unchanged, got=%s", string(out))
+	}
+}
+
 type failingOrCompletionDoer struct {
 	completionResp *http.Response
 }
@@ -134,3 +219,33 @@ func (d failingOrCompletionDoer) Do(req *http.Request) (*http.Response, error) {
 	}
 	return nil, errors.New("forced stream failure")
 }
+
+func TestAutoContinuePreservesIncompleteStateWhenNextChunkOmitsStatus(t *testing.T) {
+	initialBody := strings.Join([]string{
+		`data: {"response_message_id":321,"v":{"response":{"message_id":321,"status":"INCOMPLETE"}}}`,
+		`data: {"p":"response/content","v":{"text":"continued"}}`,
+		`data: [DONE]`,
+	}, "\n") + "\n"
+
+	var continueCalls atomic.Int32
+	body := newAutoContinueBody(context.Background(), io.NopCloser(strings.NewReader(initialBody)), "session-123", 8, func(context.Context, string, int) (*http.Response, error) {
+		continueCalls.Add(1)
+		return &http.Response{
+			StatusCode: http.StatusOK,
+			Header:     make(http.Header),
+			Body: io.NopCloser(strings.NewReader(
+				`data: {"response_message_id":322,"p":"response/status","v":"FINISHED"}` + "\n" +
+					`data: [DONE]` + "\n",
+			)),
+		}, nil
+	})
+	defer func() { _ = body.Close() }()
+
+	_, err := io.ReadAll(body)
+	if err != nil {
+		t.Fatalf("read body failed: %v", err)
+	}
+	if continueCalls.Load() != 1 {
+		t.Fatalf("expected exactly one continue call, got %d", continueCalls.Load())
+	}
+}

internal/deepseek/protocol/constants_shared.json

@@ -2,7 +2,7 @@
   "client": {
     "name": "DeepSeek",
     "platform": "android",
-    "version": "2.0.1",
+    "version": "2.0.3",
     "android_api_level": "35",
     "locale": "zh_CN"
   },

internal/devcapture/store.go

@@ -10,6 +10,8 @@ import (
 	"sync"
 	"time"
 
+	"ds2api/internal/util"
+
 	"github.com/google/uuid"
 )
 
@@ -194,7 +196,8 @@ func (c *captureBody) append(chunk string) {
 	}
 	remain := maxLen - current
 	if len(chunk) > remain {
-		c.buf.WriteString(chunk[:remain])
+		truncated, _ := util.TruncateUTF8Bytes(chunk, remain)
+		c.buf.WriteString(truncated)
 		c.truncated = true
 		return
 	}

internal/devcapture/store_test.go

@@ -4,6 +4,7 @@ import (
 	"io"
 	"strings"
 	"testing"
+	"unicode/utf8"
 )
 
 func TestNewFromEnvDefaults(t *testing.T) {
@@ -82,3 +83,28 @@ func TestWrapBodyTruncatesByLimit(t *testing.T) {
 		t.Fatalf("expected account id, got %q", items[0].AccountID)
 	}
 }
+
+func TestWrapBodyTruncatesUTF8WithoutBreakingRune(t *testing.T) {
+	s := &Store{enabled: true, limit: 5, maxBodyBytes: 5}
+	session := s.Start("test", "http://x", "acc1", map[string]any{"x": 1})
+	if session == nil {
+		t.Fatal("expected session")
+	}
+	rc := session.WrapBody(io.NopCloser(strings.NewReader("😀xy")), 200)
+	_, _ = io.ReadAll(rc)
+	_ = rc.Close()
+
+	items := s.Snapshot()
+	if len(items) != 1 {
+		t.Fatalf("expected 1 item, got %d", len(items))
+	}
+	if !utf8.ValidString(items[0].ResponseBody) {
+		t.Fatalf("expected valid utf-8 response body, got %q", items[0].ResponseBody)
+	}
+	if items[0].ResponseBody != "😀x" {
+		t.Fatalf("expected rune-safe truncation, got %q", items[0].ResponseBody)
+	}
+	if !items[0].ResponseTruncated {
+		t.Fatal("expected truncated flag true")
+	}
+}

internal/format/claude/render.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"time"
 
+	"ds2api/internal/prompt"
 	"ds2api/internal/util"
 )
 
@@ -43,8 +44,23 @@ func BuildMessageResponse(messageID, model string, normalizedMessages []any, fin
 		"stop_reason":   stopReason,
 		"stop_sequence": nil,
 		"usage": map[string]any{
-			"input_tokens":  util.EstimateTokens(fmt.Sprintf("%v", normalizedMessages)),
-			"output_tokens": util.EstimateTokens(finalThinking) + util.EstimateTokens(finalText),
+			"input_tokens":  util.CountPromptTokens(prompt.MessagesPrepareWithThinking(claudeMessageMaps(normalizedMessages), false), model),
+			"output_tokens": util.CountOutputTokens(finalThinking, model) + util.CountOutputTokens(finalText, model),
 		},
 	}
 }
+
+func claudeMessageMaps(messages []any) []map[string]any {
+	if len(messages) == 0 {
+		return nil
+	}
+	out := make([]map[string]any, 0, len(messages))
+	for _, item := range messages {
+		msg, ok := item.(map[string]any)
+		if !ok {
+			continue
+		}
+		out = append(out, msg)
+	}
+	return out
+}

internal/format/openai/render_chat.go

@@ -29,7 +29,7 @@ func BuildChatCompletionWithToolCalls(completionID, model, finalPrompt, finalThi
 		"created": time.Now().Unix(),
 		"model":   model,
 		"choices": []map[string]any{{"index": 0, "message": messageObj, "finish_reason": finishReason}},
-		"usage":   BuildChatUsage(finalPrompt, finalThinking, finalText),
+		"usage":   BuildChatUsageForModel(model, finalPrompt, finalThinking, finalText, 0),
 	}
 }
 

internal/format/openai/render_responses.go

@@ -70,7 +70,7 @@ func BuildResponseObjectFromItems(responseID, model, finalPrompt, finalThinking,
 		"model":       model,
 		"output":      output,
 		"output_text": outputText,
-		"usage":       BuildResponsesUsage(finalPrompt, finalThinking, finalText),
+		"usage":       BuildResponsesUsageForModel(model, finalPrompt, finalThinking, finalText, 0),
 	}
 }
 

internal/format/openai/render_test.go

@@ -6,6 +6,7 @@ import (
 	"testing"
 
 	"ds2api/internal/toolcall"
+	"ds2api/internal/util"
 )
 
 func TestBuildResponseObjectKeepsFencedToolPayloadAsText(t *testing.T) {
@@ -177,3 +178,17 @@ func TestBuildResponseObjectWithToolCallsCoercesSchemaDeclaredStringArguments(t
 		t.Fatalf("expected response content stringified by schema, got %#v", args["content"])
 	}
 }
+
+func TestBuildChatUsageForModelUsesConservativePromptCount(t *testing.T) {
+	prompt := strings.Repeat("上下文token ", 40)
+	usage := BuildChatUsageForModel("deepseek-v4-flash", prompt, "", "ok", 0)
+	promptTokens, _ := usage["prompt_tokens"].(int)
+	if promptTokens <= util.EstimateTokens(prompt) {
+		t.Fatalf("expected conservative prompt token count > rough estimate, got=%d estimate=%d", promptTokens, util.EstimateTokens(prompt))
+	}
+	totalTokens, _ := usage["total_tokens"].(int)
+	completionTokens, _ := usage["completion_tokens"].(int)
+	if totalTokens != promptTokens+completionTokens {
+		t.Fatalf("expected total tokens to add up, got usage=%#v", usage)
+	}
+}

internal/format/openai/render_usage.go

@@ -2,10 +2,10 @@ package openai
 
 import "ds2api/internal/util"
 
-func BuildChatUsage(finalPrompt, finalThinking, finalText string) map[string]any {
-	promptTokens := util.EstimateTokens(finalPrompt)
-	reasoningTokens := util.EstimateTokens(finalThinking)
-	completionTokens := util.EstimateTokens(finalText)
+func BuildChatUsageForModel(model, finalPrompt, finalThinking, finalText string, refFileTokens int) map[string]any {
+	promptTokens := util.CountPromptTokens(finalPrompt, model) + refFileTokens
+	reasoningTokens := util.CountOutputTokens(finalThinking, model)
+	completionTokens := util.CountOutputTokens(finalText, model)
 	return map[string]any{
 		"prompt_tokens":     promptTokens,
 		"completion_tokens": reasoningTokens + completionTokens,
@@ -16,13 +16,21 @@ func BuildChatUsage(finalPrompt, finalThinking, finalText string) map[string]any
 	}
 }
 
-func BuildResponsesUsage(finalPrompt, finalThinking, finalText string) map[string]any {
-	promptTokens := util.EstimateTokens(finalPrompt)
-	reasoningTokens := util.EstimateTokens(finalThinking)
-	completionTokens := util.EstimateTokens(finalText)
+func BuildChatUsage(finalPrompt, finalThinking, finalText string) map[string]any {
+	return BuildChatUsageForModel("", finalPrompt, finalThinking, finalText, 0)
+}
+
+func BuildResponsesUsageForModel(model, finalPrompt, finalThinking, finalText string, refFileTokens int) map[string]any {
+	promptTokens := util.CountPromptTokens(finalPrompt, model) + refFileTokens
+	reasoningTokens := util.CountOutputTokens(finalThinking, model)
+	completionTokens := util.CountOutputTokens(finalText, model)
 	return map[string]any{
 		"input_tokens":  promptTokens,
 		"output_tokens": reasoningTokens + completionTokens,
 		"total_tokens":  promptTokens + reasoningTokens + completionTokens,
 	}
 }
+
+func BuildResponsesUsage(finalPrompt, finalThinking, finalText string) map[string]any {
+	return BuildResponsesUsageForModel("", finalPrompt, finalThinking, finalText, 0)
+}

internal/httpapi/admin/accounts/handler_accounts_testing.go

@@ -107,6 +107,7 @@ func (h *Handler) testAccount(ctx context.Context, acc config.Account, model, me
 		"model":           model,
 		"session_count":   0,
 		"config_writable": !h.Store.IsEnvBacked(),
+		"config_warning":  "",
 	}
 	defer func() {
 		status := "failed"
@@ -121,8 +122,7 @@ func (h *Handler) testAccount(ctx context.Context, acc config.Account, model, me
 		return result
 	}
 	if err := h.Store.UpdateAccountToken(acc.Identifier(), token); err != nil {
-		result["message"] = "登录成功但写入运行时 token 失败: " + err.Error()
-		return result
+		result["config_warning"] = "登录成功，但 token 持久化失败（仅保存在内存，重启后会丢失）: " + err.Error()
 	}
 	authCtx := &authn.RequestAuth{UseConfigToken: false, DeepSeekToken: token, AccountID: identifier, Account: acc}
 	proxyCtx := authn.WithAuth(ctx, authCtx)
@@ -136,8 +136,7 @@ func (h *Handler) testAccount(ctx context.Context, acc config.Account, model, me
 		token = newToken
 		authCtx.DeepSeekToken = token
 		if err := h.Store.UpdateAccountToken(acc.Identifier(), token); err != nil {
-			result["message"] = "刷新 token 成功但写入运行时 token 失败: " + err.Error()
-			return result
+			result["config_warning"] = "刷新 token 成功，但 token 持久化失败（仅保存在内存，重启后会丢失）: " + err.Error()
 		}
 		sessionID, err = h.DS.CreateSession(proxyCtx, authCtx, 1)
 		if err != nil {
@@ -155,6 +154,9 @@ func (h *Handler) testAccount(ctx context.Context, acc config.Account, model, me
 	if strings.TrimSpace(message) == "" {
 		result["success"] = true
 		result["message"] = "Token 刷新成功（登录与会话创建成功）"
+		if warning, _ := result["config_warning"].(string); strings.TrimSpace(warning) != "" {
+			result["message"] = result["message"].(string) + "；" + warning
+		}
 		result["response_time"] = int(time.Since(start).Milliseconds())
 		return result
 	}

internal/httpapi/admin/rawsamples/handler_raw_samples.go

@@ -15,6 +15,7 @@ import (
 	"ds2api/internal/devcapture"
 	adminshared "ds2api/internal/httpapi/admin/shared"
 	"ds2api/internal/rawsample"
+	"ds2api/internal/util"
 )
 
 type captureChain struct {
@@ -479,10 +480,13 @@ func previewCaptureChainResponse(chain captureChain) string {
 
 func previewText(text string, limit int) string {
 	text = strings.TrimSpace(text)
-	if limit <= 0 || len(text) <= limit {
+	if limit <= 0 {
 		return text
 	}
-	return text[:limit] + "..."
+	if truncated, ok := util.TruncateRunes(text, limit); ok {
+		return truncated + "..."
+	}
+	return text
 }
 
 func captureChainHasTruncatedResponse(chain captureChain) bool {

internal/httpapi/admin/rawsamples/handler_raw_samples_test.go

@@ -10,6 +10,7 @@ import (
 	"path/filepath"
 	"strings"
 	"testing"
+	"unicode/utf8"
 
 	"ds2api/internal/devcapture"
 )
@@ -231,6 +232,16 @@ func TestCombineCaptureBodiesPreservesOrderAndSeparators(t *testing.T) {
 	}
 }
 
+func TestPreviewTextPreservesUTF8MB4Characters(t *testing.T) {
+	preview := previewText(strings.Repeat("😀", 281), 280)
+	if !utf8.ValidString(preview) {
+		t.Fatalf("expected valid utf-8 preview, got %q", preview)
+	}
+	if preview != strings.Repeat("😀", 280)+"..." {
+		t.Fatalf("unexpected preview: %q", preview)
+	}
+}
+
 func TestQueryRawSampleCapturesGroupsBySessionAndMatchesQuestion(t *testing.T) {
 	devcapture.Global().Clear()
 	defer devcapture.Global().Clear()

internal/httpapi/claude/handler_helpers_misc.go

@@ -1,6 +1,7 @@
 package claude
 
 import (
+	"ds2api/internal/toolcall"
 	"fmt"
 	"strings"
 )
@@ -31,30 +32,9 @@ func extractClaudeToolNames(tools []any) []string {
 }
 
 func extractClaudeToolMeta(m map[string]any) (string, string, any) {
-	name, _ := m["name"].(string)
-	desc, _ := m["description"].(string)
-	schemaObj := m["input_schema"]
-	if schemaObj == nil {
-		schemaObj = m["parameters"]
-	}
-
-	if fn, ok := m["function"].(map[string]any); ok {
-		if strings.TrimSpace(name) == "" {
-			name, _ = fn["name"].(string)
-		}
-		if strings.TrimSpace(desc) == "" {
-			desc, _ = fn["description"].(string)
-		}
-		if schemaObj == nil {
-			if v, ok := fn["input_schema"]; ok {
-				schemaObj = v
-			}
-		}
-		if schemaObj == nil {
-			if v, ok := fn["parameters"]; ok {
-				schemaObj = v
-			}
-		}
+	name, desc, schemaObj := toolcall.ExtractToolMeta(m)
+	if strings.TrimSpace(desc) == "" {
+		desc = "No description available"
 	}
 	return strings.TrimSpace(name), strings.TrimSpace(desc), schemaObj
 }

internal/httpapi/claude/handler_messages.go

@@ -177,7 +177,7 @@ func stripClaudeThinkingBlocks(raw []byte) []byte {
 	return out
 }
 
-func (h *Handler) handleClaudeStreamRealtime(w http.ResponseWriter, r *http.Request, resp *http.Response, model string, messages []any, thinkingEnabled, searchEnabled bool, toolNames []string) {
+func (h *Handler) handleClaudeStreamRealtime(w http.ResponseWriter, r *http.Request, resp *http.Response, model string, messages []any, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any) {
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
@@ -205,6 +205,8 @@ func (h *Handler) handleClaudeStreamRealtime(w http.ResponseWriter, r *http.Requ
 		searchEnabled,
 		h.compatStripReferenceMarkers(),
 		toolNames,
+		toolsRaw,
+		buildClaudePromptTokenText(messages, thinkingEnabled),
 	)
 	streamRuntime.sendMessageStart()
 

internal/httpapi/claude/handler_stream_test.go

@@ -81,7 +81,7 @@ func TestHandleClaudeStreamRealtimeTextIncrementsWithEventHeaders(t *testing.T)
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
 
-	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, false, false, nil)
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, false, false, nil, nil)
 
 	body := rec.Body.String()
 	if !strings.Contains(body, "event: message_start") {
@@ -122,7 +122,7 @@ func TestHandleClaudeStreamRealtimeThinkingDelta(t *testing.T) {
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
 
-	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, true, false, nil)
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, true, false, nil, nil)
 
 	frames := parseClaudeFrames(t, rec.Body.String())
 	foundThinkingDelta := false
@@ -149,7 +149,7 @@ func TestHandleClaudeStreamRealtimeSkipsThinkingFallbackWhenFinalTextExists(t *t
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
 
-	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "use tool"}}, true, false, []string{"search"})
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "use tool"}}, true, false, []string{"search"}, nil)
 
 	frames := parseClaudeFrames(t, rec.Body.String())
 	for _, f := range findClaudeFrames(frames, "content_block_start") {
@@ -180,7 +180,7 @@ func TestHandleClaudeStreamRealtimeUpstreamErrorEvent(t *testing.T) {
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
 
-	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, false, false, nil)
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, false, false, nil, nil)
 
 	frames := parseClaudeFrames(t, rec.Body.String())
 	errFrames := findClaudeFrames(frames, "error")
@@ -217,7 +217,7 @@ func TestHandleClaudeStreamRealtimePingEvent(t *testing.T) {
 
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
-	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, false, false, nil)
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "hi"}}, false, false, nil, nil)
 
 	frames := parseClaudeFrames(t, rec.Body.String())
 	if len(findClaudeFrames(frames, "ping")) == 0 {
@@ -271,7 +271,7 @@ func TestHandleClaudeStreamRealtimeToolSafetyAcrossStructuredFormats(t *testing.
 			rec := httptest.NewRecorder()
 			req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
 
-			h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "use tool"}}, false, false, []string{"Bash"})
+			h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "use tool"}}, false, false, []string{"Bash"}, nil)
 
 			frames := parseClaudeFrames(t, rec.Body.String())
 			foundToolUse := false
@@ -299,7 +299,7 @@ func TestHandleClaudeStreamRealtimeDetectsToolUseWithLeadingProse(t *testing.T)
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
 
-	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "use tool"}}, false, false, []string{"write_file"})
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "use tool"}}, false, false, []string{"write_file"}, nil)
 
 	frames := parseClaudeFrames(t, rec.Body.String())
 	foundToolUse := false
@@ -333,7 +333,7 @@ func TestHandleClaudeStreamRealtimeIgnoresUnclosedFencedToolExample(t *testing.T
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
 
-	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "show example only"}}, false, false, []string{"Bash"})
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "show example only"}}, false, false, []string{"Bash"}, nil)
 
 	frames := parseClaudeFrames(t, rec.Body.String())
 	foundToolUse := false
@@ -365,3 +365,48 @@ func TestHandleClaudeStreamRealtimeIgnoresUnclosedFencedToolExample(t *testing.T
 func TestHandleClaudeStreamRealtimePromotesUnclosedFencedToolExample(t *testing.T) {
 	TestHandleClaudeStreamRealtimeIgnoresUnclosedFencedToolExample(t)
 }
+
+func TestHandleClaudeStreamRealtimeNormalizesToolInputBySchema(t *testing.T) {
+	h := &Handler{}
+	resp := makeClaudeSSEHTTPResponse(
+		`data: {"p":"response/content","v":"<tool_calls><invoke name=\"Write\">{\"input\":{\"content\":{\"message\":\"hi\"},\"taskId\":1}}</invoke></tool_calls>"}`,
+		`data: [DONE]`,
+	)
+	rec := httptest.NewRecorder()
+	req := httptest.NewRequest(http.MethodPost, "/anthropic/v1/messages", nil)
+	toolsRaw := []any{
+		map[string]any{
+			"name": "Write",
+			"inputSchema": map[string]any{
+				"type": "object",
+				"properties": map[string]any{
+					"content": map[string]any{"type": "string"},
+					"taskId":  map[string]any{"type": "string"},
+				},
+			},
+		},
+	}
+
+	h.handleClaudeStreamRealtime(rec, req, resp, "claude-sonnet-4-5", []any{map[string]any{"role": "user", "content": "write"}}, false, false, []string{"Write"}, toolsRaw)
+
+	frames := parseClaudeFrames(t, rec.Body.String())
+	for _, f := range findClaudeFrames(frames, "content_block_delta") {
+		delta, _ := f.Payload["delta"].(map[string]any)
+		if delta["type"] != "input_json_delta" {
+			continue
+		}
+		partial := asString(delta["partial_json"])
+		var args map[string]any
+		if err := json.Unmarshal([]byte(partial), &args); err != nil {
+			t.Fatalf("decode partial_json failed: %v payload=%s", err, partial)
+		}
+		if args["content"] != `{"message":"hi"}` {
+			t.Fatalf("expected content normalized to string, got %#v", args["content"])
+		}
+		if args["taskId"] != "1" {
+			t.Fatalf("expected taskId normalized to string, got %#v", args["taskId"])
+		}
+		return
+	}
+	t.Fatalf("expected input_json_delta frame, body=%s", rec.Body.String())
+}

internal/httpapi/claude/handler_tokens.go

@@ -3,8 +3,6 @@ package claude
 import (
 	"encoding/json"
 	"net/http"
-
-	"ds2api/internal/util"
 )
 
 func (h *Handler) CountTokens(w http.ResponseWriter, r *http.Request) {
@@ -26,26 +24,11 @@ func (h *Handler) CountTokens(w http.ResponseWriter, r *http.Request) {
 		writeClaudeError(w, http.StatusBadRequest, "Request must include 'model' and 'messages'.")
 		return
 	}
-	inputTokens := 0
-	if sys, ok := req["system"].(string); ok {
-		inputTokens += util.EstimateTokens(sys)
-	}
-	for _, item := range messages {
-		msg, ok := item.(map[string]any)
-		if !ok {
-			continue
-		}
-		inputTokens += 2
-		inputTokens += util.EstimateTokens(extractMessageContent(msg["content"]))
-	}
-	if tools, ok := req["tools"].([]any); ok {
-		for _, t := range tools {
-			b, _ := json.Marshal(t)
-			inputTokens += util.EstimateTokens(string(b))
-		}
-	}
-	if inputTokens < 1 {
-		inputTokens = 1
+	normalized, err := normalizeClaudeRequest(h.Store, req)
+	if err != nil {
+		writeClaudeError(w, http.StatusBadRequest, err.Error())
+		return
 	}
+	inputTokens := countClaudeInputTokens(normalized.Standard)
 	writeJSON(w, http.StatusOK, map[string]any{"input_tokens": inputTokens})
 }

internal/httpapi/claude/prompt_token_text.go

@@ -0,0 +1,7 @@
+package claude
+
+import "ds2api/internal/prompt"
+
+func buildClaudePromptTokenText(messages []any, thinkingEnabled bool) string {
+	return prompt.MessagesPrepareWithThinking(toMessageMaps(messages), thinkingEnabled)
+}

internal/httpapi/claude/standard_request.go

@@ -48,16 +48,18 @@ func normalizeClaudeRequest(store ConfigReader, req map[string]any) (claudeNorma
 
 	return claudeNormalizedRequest{
 		Standard: promptcompat.StandardRequest{
-			Surface:        "anthropic_messages",
-			RequestedModel: strings.TrimSpace(model),
-			ResolvedModel:  dsModel,
-			ResponseModel:  strings.TrimSpace(model),
-			Messages:       payload["messages"].([]any),
-			FinalPrompt:    finalPrompt,
-			ToolNames:      toolNames,
-			Stream:         util.ToBool(req["stream"]),
-			Thinking:       thinkingEnabled,
-			Search:         searchEnabled,
+			Surface:         "anthropic_messages",
+			RequestedModel:  strings.TrimSpace(model),
+			ResolvedModel:   dsModel,
+			ResponseModel:   strings.TrimSpace(model),
+			Messages:        payload["messages"].([]any),
+			PromptTokenText: finalPrompt,
+			ToolsRaw:        toolsRequested,
+			FinalPrompt:     finalPrompt,
+			ToolNames:       toolNames,
+			Stream:          util.ToBool(req["stream"]),
+			Thinking:        thinkingEnabled,
+			Search:          searchEnabled,
 		},
 		NormalizedMessages: normalizedMessages,
 	}, nil

internal/httpapi/claude/standard_request_test.go

@@ -32,11 +32,39 @@ func TestNormalizeClaudeRequest(t *testing.T) {
 	if len(norm.Standard.ToolNames) == 0 {
 		t.Fatalf("expected tool names")
 	}
+	if norm.Standard.ToolsRaw == nil {
+		t.Fatalf("expected ToolsRaw preserved for downstream normalization")
+	}
 	if norm.Standard.FinalPrompt == "" {
 		t.Fatalf("expected non-empty final prompt")
 	}
 }
 
+func TestNormalizeClaudeRequestSupportsCamelCaseInputSchemaPromptInjection(t *testing.T) {
+	t.Setenv("DS2API_CONFIG_JSON", `{}`)
+	store := config.LoadStore()
+	req := map[string]any{
+		"model": "claude-sonnet-4-5",
+		"messages": []any{
+			map[string]any{"role": "user", "content": "hello"},
+		},
+		"tools": []any{
+			map[string]any{
+				"name":        "todowrite",
+				"description": "Write todos",
+				"inputSchema": map[string]any{"type": "object", "properties": map[string]any{"todos": map[string]any{"type": "array"}}},
+			},
+		},
+	}
+	norm, err := normalizeClaudeRequest(store, req)
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+	if !containsStr(norm.Standard.FinalPrompt, `"type":"array"`) {
+		t.Fatalf("expected inputSchema to be injected into prompt, got=%q", norm.Standard.FinalPrompt)
+	}
+}
+
 func TestNormalizeClaudeRequestInjectsToolsIntoExistingSystemMessage(t *testing.T) {
 	t.Setenv("DS2API_CONFIG_JSON", `{}`)
 	store := config.LoadStore()

internal/httpapi/claude/stream_runtime_core.go

@@ -15,9 +15,11 @@ type claudeStreamRuntime struct {
 	rc       *http.ResponseController
 	canFlush bool
 
-	model     string
-	toolNames []string
-	messages  []any
+	model           string
+	toolNames       []string
+	messages        []any
+	toolsRaw        any
+	promptTokenText string
 
 	thinkingEnabled       bool
 	searchEnabled         bool
@@ -47,6 +49,8 @@ func newClaudeStreamRuntime(
 	searchEnabled bool,
 	stripReferenceMarkers bool,
 	toolNames []string,
+	toolsRaw any,
+	promptTokenText string,
 ) *claudeStreamRuntime {
 	return &claudeStreamRuntime{
 		w:                     w,
@@ -59,6 +63,8 @@ func newClaudeStreamRuntime(
 		bufferToolContent:     len(toolNames) > 0,
 		stripReferenceMarkers: stripReferenceMarkers,
 		toolNames:             toolNames,
+		toolsRaw:              toolsRaw,
+		promptTokenText:       promptTokenText,
 		messageID:             fmt.Sprintf("msg_%d", time.Now().UnixNano()),
 		thinkingBlockIndex:    -1,
 		textBlockIndex:        -1,

internal/httpapi/claude/stream_runtime_emit.go

@@ -42,7 +42,10 @@ func (s *claudeStreamRuntime) sendPing() {
 }
 
 func (s *claudeStreamRuntime) sendMessageStart() {
-	inputTokens := util.EstimateTokens(fmt.Sprintf("%v", s.messages))
+	inputTokens := countClaudeInputTokensFromText(s.promptTokenText, s.model)
+	if inputTokens == 0 {
+		inputTokens = util.CountPromptTokens(fmt.Sprintf("%v", s.messages), s.model)
+	}
 	s.send("message_start", map[string]any{
 		"type": "message_start",
 		"message": map[string]any{

internal/httpapi/claude/stream_runtime_finalize.go

@@ -52,6 +52,7 @@ func (s *claudeStreamRuntime) finalize(stopReason string) {
 			detected = toolcall.ParseStandaloneToolCalls(finalThinking, s.toolNames)
 		}
 		if len(detected) > 0 {
+			detected = toolcall.NormalizeParsedToolCallsForSchemas(detected, s.toolsRaw)
 			stopReason = "tool_use"
 			for i, tc := range detected {
 				idx := s.nextBlockIndex + i
@@ -108,7 +109,7 @@ func (s *claudeStreamRuntime) finalize(stopReason string) {
 		}
 	}
 
-	outputTokens := util.EstimateTokens(finalThinking) + util.EstimateTokens(finalText)
+	outputTokens := util.CountOutputTokens(finalThinking, s.model) + util.CountOutputTokens(finalText, s.model)
 	s.send("message_delta", map[string]any{
 		"type": "message_delta",
 		"delta": map[string]any{

internal/httpapi/claude/token_count.go

@@ -0,0 +1,20 @@
+package claude
+
+import (
+	"strings"
+
+	"ds2api/internal/promptcompat"
+	"ds2api/internal/util"
+)
+
+func countClaudeInputTokens(stdReq promptcompat.StandardRequest) int {
+	promptText := stdReq.PromptTokenText
+	if strings.TrimSpace(promptText) == "" {
+		promptText = stdReq.FinalPrompt
+	}
+	return countClaudeInputTokensFromText(promptText, stdReq.ResolvedModel)
+}
+
+func countClaudeInputTokensFromText(promptText, model string) int {
+	return util.CountPromptTokens(promptText, model)
+}

internal/httpapi/gemini/convert_request.go

@@ -36,16 +36,17 @@ func normalizeGeminiRequest(store ConfigReader, routeModel string, req map[strin
 	passThrough := collectGeminiPassThrough(req)
 
 	return promptcompat.StandardRequest{
-		Surface:        "google_gemini",
-		RequestedModel: requestedModel,
-		ResolvedModel:  resolvedModel,
-		ResponseModel:  requestedModel,
-		Messages:       messagesRaw,
-		FinalPrompt:    finalPrompt,
-		ToolNames:      toolNames,
-		Stream:         stream,
-		Thinking:       thinkingEnabled,
-		Search:         searchEnabled,
-		PassThrough:    passThrough,
+		Surface:         "google_gemini",
+		RequestedModel:  requestedModel,
+		ResolvedModel:   resolvedModel,
+		ResponseModel:   requestedModel,
+		Messages:        messagesRaw,
+		PromptTokenText: finalPrompt,
+		FinalPrompt:     finalPrompt,
+		ToolNames:       toolNames,
+		Stream:          stream,
+		Thinking:        thinkingEnabled,
+		Search:          searchEnabled,
+		PassThrough:     passThrough,
 	}, nil
 }

internal/httpapi/gemini/handler_generate.go

@@ -227,7 +227,7 @@ func (h *Handler) handleNonStreamGenerateContent(w http.ResponseWriter, resp *ht
 //nolint:unused // retained for native Gemini non-stream handling path.
 func buildGeminiGenerateContentResponse(model, finalPrompt, finalThinking, finalText string, toolNames []string) map[string]any {
 	parts := buildGeminiPartsFromFinal(finalText, finalThinking, toolNames)
-	usage := buildGeminiUsage(finalPrompt, finalThinking, finalText)
+	usage := buildGeminiUsage(model, finalPrompt, finalThinking, finalText)
 	return map[string]any{
 		"candidates": []map[string]any{
 			{
@@ -245,10 +245,10 @@ func buildGeminiGenerateContentResponse(model, finalPrompt, finalThinking, final
 }
 
 //nolint:unused // retained for native Gemini non-stream handling path.
-func buildGeminiUsage(finalPrompt, finalThinking, finalText string) map[string]any {
-	promptTokens := util.EstimateTokens(finalPrompt)
-	reasoningTokens := util.EstimateTokens(finalThinking)
-	completionTokens := util.EstimateTokens(finalText)
+func buildGeminiUsage(model, finalPrompt, finalThinking, finalText string) map[string]any {
+	promptTokens := util.CountPromptTokens(finalPrompt, model)
+	reasoningTokens := util.CountOutputTokens(finalThinking, model)
+	completionTokens := util.CountOutputTokens(finalText, model)
 	return map[string]any{
 		"promptTokenCount":     promptTokens,
 		"candidatesTokenCount": reasoningTokens + completionTokens,

internal/httpapi/gemini/handler_stream_runtime.go

@@ -194,6 +194,6 @@ func (s *geminiStreamRuntime) finalize() {
 			},
 		},
 		"modelVersion":  s.model,
-		"usageMetadata": buildGeminiUsage(s.finalPrompt, finalThinking, finalText),
+		"usageMetadata": buildGeminiUsage(s.model, s.finalPrompt, finalThinking, finalText),
 	})
 }

internal/httpapi/openai/chat/chat_history_test.go

@@ -126,6 +126,7 @@ func TestStartChatHistoryRecoversFromTransientWriteFailure(t *testing.T) {
 	session := startChatHistory(historyStore, req, a, stdReq)
 	if session == nil {
 		t.Fatalf("expected session even when initial persistence fails")
+		return
 	}
 	if session.disabled {
 		t.Fatalf("expected session to remain active after transient start failure")
@@ -194,7 +195,7 @@ func TestHandleStreamContextCancelledMarksHistoryStopped(t *testing.T) {
 	rec := httptest.NewRecorder()
 	resp := makeOpenAISSEHTTPResponse(`data: {"p":"response/content","v":"hello"}`, `data: [DONE]`)
 
-	h.handleStream(rec, req, resp, "cid-stop", "deepseek-v4-flash", "prompt", false, false, nil, nil, session)
+	h.handleStream(rec, req, resp, "cid-stop", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, session)
 
 	snapshot, err := historyStore.Snapshot()
 	if err != nil {
@@ -307,14 +308,14 @@ func TestChatCompletionsCurrentInputFilePersistsNeutralPrompt(t *testing.T) {
 	if err != nil {
 		t.Fatalf("expected detail item, got %v", err)
 	}
-	if full.HistoryText != "" {
-		t.Fatalf("expected current input file flow to leave history text empty, got %q", full.HistoryText)
-	}
 	if len(ds.uploadCalls) != 1 {
 		t.Fatalf("expected current input upload to happen, got %d", len(ds.uploadCalls))
 	}
-	if ds.uploadCalls[0].Filename != "IGNORE.txt" {
-		t.Fatalf("expected IGNORE.txt upload, got %q", ds.uploadCalls[0].Filename)
+	if ds.uploadCalls[0].Filename != "history.txt" {
+		t.Fatalf("expected history.txt upload, got %q", ds.uploadCalls[0].Filename)
+	}
+	if full.HistoryText != string(ds.uploadCalls[0].Data) {
+		t.Fatalf("expected uploaded current input file to be persisted in history text")
 	}
 	if len(full.Messages) != 1 {
 		t.Fatalf("expected neutral prompt to be the only persisted message, got %#v", full.Messages)

internal/httpapi/openai/chat/chat_stream_runtime.go

@@ -16,12 +16,13 @@ type chatStreamRuntime struct {
 	rc       *http.ResponseController
 	canFlush bool
 
-	completionID string
-	created      int64
-	model        string
-	finalPrompt  string
-	toolNames    []string
-	toolsRaw     any
+	completionID  string
+	created       int64
+	model         string
+	finalPrompt   string
+	refFileTokens int
+	toolNames     []string
+	toolsRaw      any
 
 	thinkingEnabled       bool
 	searchEnabled         bool
@@ -36,8 +37,10 @@ type chatStreamRuntime struct {
 	toolSieve             toolstream.State
 	streamToolCallIDs     map[int]string
 	streamToolNames       map[int]string
+	rawThinking           strings.Builder
 	thinking              strings.Builder
 	toolDetectionThinking strings.Builder
+	rawText               strings.Builder
 	text                  strings.Builder
 	responseMessageID     int
 
@@ -141,7 +144,7 @@ func (s *chatStreamRuntime) finalize(finishReason string, deferEmptyOutput bool)
 	finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers)
 	s.finalThinking = finalThinking
 	s.finalText = finalText
-	detected := detectAssistantToolCalls(finalText, finalThinking, finalToolDetectionThinking, s.toolNames)
+	detected := detectAssistantToolCalls(s.rawText.String(), finalText, s.rawThinking.String(), finalToolDetectionThinking, s.toolNames)
 	if len(detected.Calls) > 0 && !s.toolCallsDoneEmitted {
 		finishReason = "tool_calls"
 		delta := map[string]any{
@@ -186,7 +189,7 @@ func (s *chatStreamRuntime) finalize(finishReason string, deferEmptyOutput bool)
 				continue
 			}
 			cleaned := cleanVisibleOutput(evt.Content, s.stripReferenceMarkers)
-			if cleaned == "" {
+			if cleaned == "" || (s.searchEnabled && sse.IsCitation(cleaned)) {
 				continue
 			}
 			delta := map[string]any{
@@ -220,7 +223,7 @@ func (s *chatStreamRuntime) finalize(finishReason string, deferEmptyOutput bool)
 		s.sendFailedChunk(status, message, code)
 		return true
 	}
-	usage := openaifmt.BuildChatUsage(s.finalPrompt, finalThinking, finalText)
+	usage := openaifmt.BuildChatUsageForModel(s.model, s.finalPrompt, finalThinking, finalText, s.refFileTokens)
 	s.finalFinishReason = finishReason
 	s.finalUsage = usage
 	s.sendChunk(openaifmt.BuildChatStreamChunk(
@@ -263,21 +266,22 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 		}
 	}
 	for _, p := range parsed.Parts {
-		cleanedText := cleanVisibleOutput(p.Text, s.stripReferenceMarkers)
-		if s.searchEnabled && sse.IsCitation(cleanedText) {
-			continue
-		}
-		if cleanedText == "" {
-			continue
-		}
-		contentSeen = true
 		delta := map[string]any{}
 		if !s.firstChunkSent {
 			delta["role"] = "assistant"
 			s.firstChunkSent = true
 		}
 		if p.Type == "thinking" {
+			rawTrimmed := sse.TrimContinuationOverlap(s.rawThinking.String(), p.Text)
+			if rawTrimmed != "" {
+				s.rawThinking.WriteString(rawTrimmed)
+				contentSeen = true
+			}
 			if s.thinkingEnabled {
+				cleanedText := cleanVisibleOutput(rawTrimmed, s.stripReferenceMarkers)
+				if cleanedText == "" {
+					continue
+				}
 				trimmed := sse.TrimContinuationOverlap(s.thinking.String(), cleanedText)
 				if trimmed == "" {
 					continue
@@ -286,15 +290,27 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 				delta["reasoning_content"] = trimmed
 			}
 		} else {
-			trimmed := sse.TrimContinuationOverlap(s.text.String(), cleanedText)
-			if trimmed == "" {
+			rawTrimmed := sse.TrimContinuationOverlap(s.rawText.String(), p.Text)
+			if rawTrimmed == "" {
 				continue
 			}
-			s.text.WriteString(trimmed)
+			s.rawText.WriteString(rawTrimmed)
+			contentSeen = true
+			cleanedText := cleanVisibleOutput(rawTrimmed, s.stripReferenceMarkers)
+			if s.searchEnabled && sse.IsCitation(cleanedText) {
+				continue
+			}
+			trimmed := sse.TrimContinuationOverlap(s.text.String(), cleanedText)
+			if trimmed != "" {
+				s.text.WriteString(trimmed)
+			}
 			if !s.bufferToolContent {
+				if trimmed == "" {
+					continue
+				}
 				delta["content"] = trimmed
 			} else {
-				events := toolstream.ProcessChunk(&s.toolSieve, trimmed, s.toolNames)
+				events := toolstream.ProcessChunk(&s.toolSieve, rawTrimmed, s.toolNames)
 				for _, evt := range events {
 					if len(evt.ToolCallDeltas) > 0 {
 						if !s.emitEarlyToolDeltas {
@@ -335,7 +351,7 @@ func (s *chatStreamRuntime) onParsed(parsed sse.LineResult) streamengine.ParsedD
 					}
 					if evt.Content != "" {
 						cleaned := cleanVisibleOutput(evt.Content, s.stripReferenceMarkers)
-						if cleaned == "" {
+						if cleaned == "" || (s.searchEnabled && sse.IsCitation(cleaned)) {
 							continue
 						}
 						contentDelta := map[string]any{

internal/httpapi/openai/chat/empty_retry_runtime.go

@@ -16,6 +16,8 @@ import (
 )
 
 type chatNonStreamResult struct {
+	rawThinking           string
+	rawText               string
 	thinking              string
 	toolDetectionThinking string
 	text                  string
@@ -26,11 +28,12 @@ type chatNonStreamResult struct {
 	responseMessageID     int
 }
 
-func (h *Handler) handleNonStreamWithRetry(w http.ResponseWriter, ctx context.Context, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
+func (h *Handler) handleNonStreamWithRetry(w http.ResponseWriter, ctx context.Context, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, completionID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
 	attempts := 0
 	currentResp := resp
 	usagePrompt := finalPrompt
 	accumulatedThinking := ""
+	accumulatedRawThinking := ""
 	accumulatedToolDetectionThinking := ""
 	for {
 		result, ok := h.collectChatNonStreamAttempt(w, currentResp, completionID, model, usagePrompt, thinkingEnabled, searchEnabled, toolNames, toolsRaw)
@@ -38,15 +41,17 @@ func (h *Handler) handleNonStreamWithRetry(w http.ResponseWriter, ctx context.Co
 			return
 		}
 		accumulatedThinking += sse.TrimContinuationOverlap(accumulatedThinking, result.thinking)
+		accumulatedRawThinking += sse.TrimContinuationOverlap(accumulatedRawThinking, result.rawThinking)
 		accumulatedToolDetectionThinking += sse.TrimContinuationOverlap(accumulatedToolDetectionThinking, result.toolDetectionThinking)
 		result.thinking = accumulatedThinking
+		result.rawThinking = accumulatedRawThinking
 		result.toolDetectionThinking = accumulatedToolDetectionThinking
-		detected := detectAssistantToolCalls(result.text, result.thinking, result.toolDetectionThinking, toolNames)
+		detected := detectAssistantToolCalls(result.rawText, result.text, result.rawThinking, result.toolDetectionThinking, toolNames)
 		result.detectedCalls = len(detected.Calls)
 		result.body = openaifmt.BuildChatCompletionWithToolCalls(completionID, model, usagePrompt, result.thinking, result.text, detected.Calls, toolsRaw)
 		result.finishReason = chatFinishReason(result.body)
 		if !shouldRetryChatNonStream(result, attempts) {
-			h.finishChatNonStreamResult(w, result, attempts, usagePrompt, historySession)
+			h.finishChatNonStreamResult(w, result, attempts, usagePrompt, refFileTokens, historySession)
 			return
 		}
 
@@ -67,7 +72,7 @@ func (h *Handler) handleNonStreamWithRetry(w http.ResponseWriter, ctx context.Co
 			config.Logger.Warn("[openai_empty_retry] retry request failed", "surface", "chat.completions", "stream", false, "retry_attempt", attempts, "error", err)
 			return
 		}
-		usagePrompt = usagePromptWithEmptyOutputRetry(finalPrompt, attempts)
+		usagePrompt = usagePromptWithEmptyOutputRetry(usagePrompt, attempts)
 		currentResp = nextResp
 	}
 }
@@ -82,16 +87,17 @@ func (h *Handler) collectChatNonStreamAttempt(w http.ResponseWriter, resp *http.
 	result := sse.CollectStream(resp, thinkingEnabled, true)
 	stripReferenceMarkers := h.compatStripReferenceMarkers()
 	finalThinking := cleanVisibleOutput(result.Thinking, stripReferenceMarkers)
-	finalToolDetectionThinking := cleanVisibleOutput(result.ToolDetectionThinking, stripReferenceMarkers)
 	finalText := cleanVisibleOutput(result.Text, stripReferenceMarkers)
 	if searchEnabled {
 		finalText = replaceCitationMarkersWithLinks(finalText, result.CitationLinks)
 	}
-	detected := detectAssistantToolCalls(finalText, finalThinking, finalToolDetectionThinking, toolNames)
+	detected := detectAssistantToolCalls(result.Text, finalText, result.Thinking, result.ToolDetectionThinking, toolNames)
 	respBody := openaifmt.BuildChatCompletionWithToolCalls(completionID, model, usagePrompt, finalThinking, finalText, detected.Calls, toolsRaw)
 	return chatNonStreamResult{
+		rawThinking:           result.Thinking,
+		rawText:               result.Text,
 		thinking:              finalThinking,
-		toolDetectionThinking: finalToolDetectionThinking,
+		toolDetectionThinking: result.ToolDetectionThinking,
 		text:                  finalText,
 		contentFilter:         result.ContentFilter,
 		detectedCalls:         len(detected.Calls),
@@ -101,7 +107,7 @@ func (h *Handler) collectChatNonStreamAttempt(w http.ResponseWriter, resp *http.
 	}, true
 }
 
-func (h *Handler) finishChatNonStreamResult(w http.ResponseWriter, result chatNonStreamResult, attempts int, usagePrompt string, historySession *chatHistorySession) {
+func (h *Handler) finishChatNonStreamResult(w http.ResponseWriter, result chatNonStreamResult, attempts int, usagePrompt string, refFileTokens int, historySession *chatHistorySession) {
 	if result.detectedCalls == 0 && shouldWriteUpstreamEmptyOutputError(result.text) {
 		status, message, code := upstreamEmptyOutputDetail(result.contentFilter, result.text, result.thinking)
 		if historySession != nil {
@@ -112,7 +118,7 @@ func (h *Handler) finishChatNonStreamResult(w http.ResponseWriter, result chatNo
 		return
 	}
 	if historySession != nil {
-		historySession.success(http.StatusOK, result.thinking, result.text, result.finishReason, openaifmt.BuildChatUsage(usagePrompt, result.thinking, result.text))
+		historySession.success(http.StatusOK, result.thinking, result.text, result.finishReason, openaifmt.BuildChatUsageForModel("", usagePrompt, result.thinking, result.text, refFileTokens))
 	}
 	writeJSON(w, http.StatusOK, result.body)
 	source := "first_attempt"
@@ -139,8 +145,8 @@ func shouldRetryChatNonStream(result chatNonStreamResult, attempts int) bool {
 		strings.TrimSpace(result.text) == ""
 }
 
-func (h *Handler) handleStreamWithRetry(w http.ResponseWriter, r *http.Request, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
-	streamRuntime, initialType, ok := h.prepareChatStreamRuntime(w, resp, completionID, model, finalPrompt, thinkingEnabled, searchEnabled, toolNames, toolsRaw, historySession)
+func (h *Handler) handleStreamWithRetry(w http.ResponseWriter, r *http.Request, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, completionID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
+	streamRuntime, initialType, ok := h.prepareChatStreamRuntime(w, resp, completionID, model, finalPrompt, refFileTokens, thinkingEnabled, searchEnabled, toolNames, toolsRaw, historySession)
 	if !ok {
 		return
 	}
@@ -182,7 +188,7 @@ func (h *Handler) handleStreamWithRetry(w http.ResponseWriter, r *http.Request,
 	}
 }
 
-func (h *Handler) prepareChatStreamRuntime(w http.ResponseWriter, resp *http.Response, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) (*chatStreamRuntime, string, bool) {
+func (h *Handler) prepareChatStreamRuntime(w http.ResponseWriter, resp *http.Response, completionID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) (*chatStreamRuntime, string, bool) {
 	if resp.StatusCode != http.StatusOK {
 		defer func() { _ = resp.Body.Close() }()
 		body, _ := io.ReadAll(resp.Body)
@@ -210,6 +216,7 @@ func (h *Handler) prepareChatStreamRuntime(w http.ResponseWriter, resp *http.Res
 		thinkingEnabled, searchEnabled, h.compatStripReferenceMarkers(), toolNames, toolsRaw,
 		len(toolNames) > 0, h.toolcallFeatureMatchEnabled() && h.toolcallEarlyEmitHighConfidence(),
 	)
+	streamRuntime.refFileTokens = refFileTokens
 	return streamRuntime, initialType, true
 }
 

internal/httpapi/openai/chat/handler.go

@@ -148,6 +148,6 @@ func formatFinalStreamToolCallsWithStableIDs(calls []toolcall.ParsedToolCall, id
 	return shared.FormatFinalStreamToolCallsWithStableIDs(calls, ids, toolsRaw)
 }
 
-func detectAssistantToolCalls(text, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult {
-	return shared.DetectAssistantToolCalls(text, exposedThinking, detectionThinking, toolNames)
+func detectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult {
+	return shared.DetectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking, toolNames)
 }

internal/httpapi/openai/chat/handler_chat.go

@@ -108,11 +108,12 @@ func (h *Handler) ChatCompletions(w http.ResponseWriter, r *http.Request) {
 		writeOpenAIError(w, http.StatusInternalServerError, "Failed to get completion.")
 		return
 	}
+	refFileTokens := stdReq.RefFileTokens
 	if stdReq.Stream {
-		h.handleStreamWithRetry(w, r, a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.FinalPrompt, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
+		h.handleStreamWithRetry(w, r, a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, refFileTokens, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
 		return
 	}
-	h.handleNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.FinalPrompt, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
+	h.handleNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, sessionID, stdReq.ResponseModel, stdReq.PromptTokenText, refFileTokens, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, historySession)
 }
 
 func (h *Handler) autoDeleteRemoteSession(ctx context.Context, a *auth.RequestAuth, sessionID string) {
@@ -148,7 +149,7 @@ func (h *Handler) autoDeleteRemoteSession(ctx context.Context, a *auth.RequestAu
 	}
 }
 
-func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
+func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, completionID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
 	if resp.StatusCode != http.StatusOK {
 		defer func() { _ = resp.Body.Close() }()
 		body, _ := io.ReadAll(resp.Body)
@@ -162,12 +163,11 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, co
 
 	stripReferenceMarkers := h.compatStripReferenceMarkers()
 	finalThinking := cleanVisibleOutput(result.Thinking, stripReferenceMarkers)
-	finalToolDetectionThinking := cleanVisibleOutput(result.ToolDetectionThinking, stripReferenceMarkers)
 	finalText := cleanVisibleOutput(result.Text, stripReferenceMarkers)
 	if searchEnabled {
 		finalText = replaceCitationMarkersWithLinks(finalText, result.CitationLinks)
 	}
-	detected := detectAssistantToolCalls(finalText, finalThinking, finalToolDetectionThinking, toolNames)
+	detected := detectAssistantToolCalls(result.Text, finalText, result.Thinking, result.ToolDetectionThinking, toolNames)
 	if shouldWriteUpstreamEmptyOutputError(finalText) && len(detected.Calls) == 0 {
 		status, message, code := upstreamEmptyOutputDetail(result.ContentFilter, finalText, finalThinking)
 		if historySession != nil {
@@ -177,6 +177,9 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, co
 		return
 	}
 	respBody := openaifmt.BuildChatCompletionWithToolCalls(completionID, model, finalPrompt, finalThinking, finalText, detected.Calls, toolsRaw)
+	if refFileTokens > 0 {
+		addRefFileTokensToUsage(respBody, refFileTokens)
+	}
 	finishReason := "stop"
 	if choices, ok := respBody["choices"].([]map[string]any); ok && len(choices) > 0 {
 		if fr, _ := choices[0]["finish_reason"].(string); strings.TrimSpace(fr) != "" {
@@ -184,12 +187,12 @@ func (h *Handler) handleNonStream(w http.ResponseWriter, resp *http.Response, co
 		}
 	}
 	if historySession != nil {
-		historySession.success(http.StatusOK, finalThinking, finalText, finishReason, openaifmt.BuildChatUsage(finalPrompt, finalThinking, finalText))
+		historySession.success(http.StatusOK, finalThinking, finalText, finishReason, openaifmt.BuildChatUsageForModel(model, finalPrompt, finalThinking, finalText, refFileTokens))
 	}
 	writeJSON(w, http.StatusOK, respBody)
 }
 
-func (h *Handler) handleStream(w http.ResponseWriter, r *http.Request, resp *http.Response, completionID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
+func (h *Handler) handleStream(w http.ResponseWriter, r *http.Request, resp *http.Response, completionID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, historySession *chatHistorySession) {
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
@@ -234,6 +237,7 @@ func (h *Handler) handleStream(w http.ResponseWriter, r *http.Request, resp *htt
 		bufferToolContent,
 		emitEarlyToolDeltas,
 	)
+	streamRuntime.refFileTokens = refFileTokens
 
 	streamengine.ConsumeSSE(streamengine.ConsumeConfig{
 		Context:             r.Context(),

internal/httpapi/openai/chat/handler_toolcall_test.go

@@ -93,7 +93,7 @@ func TestHandleNonStreamReturns429WhenUpstreamOutputEmpty(t *testing.T) {
 	)
 	rec := httptest.NewRecorder()
 
-	h.handleNonStream(rec, resp, "cid-empty", "deepseek-v4-flash", "prompt", false, false, nil, nil, nil)
+	h.handleNonStream(rec, resp, "cid-empty", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, nil)
 	if rec.Code != http.StatusTooManyRequests {
 		t.Fatalf("expected status 429 for empty upstream output, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -112,7 +112,7 @@ func TestHandleNonStreamReturnsContentFilterErrorWhenUpstreamFilteredWithoutOutp
 	)
 	rec := httptest.NewRecorder()
 
-	h.handleNonStream(rec, resp, "cid-empty-filtered", "deepseek-v4-flash", "prompt", false, false, nil, nil, nil)
+	h.handleNonStream(rec, resp, "cid-empty-filtered", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, nil)
 	if rec.Code != http.StatusBadRequest {
 		t.Fatalf("expected status 400 for filtered upstream output, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -131,7 +131,7 @@ func TestHandleNonStreamReturns429WhenUpstreamHasOnlyThinking(t *testing.T) {
 	)
 	rec := httptest.NewRecorder()
 
-	h.handleNonStream(rec, resp, "cid-thinking-only", "deepseek-v4-pro", "prompt", true, false, nil, nil, nil)
+	h.handleNonStream(rec, resp, "cid-thinking-only", "deepseek-v4-pro", "prompt", 0, true, false, nil, nil, nil)
 	if rec.Code != http.StatusTooManyRequests {
 		t.Fatalf("expected status 429 for thinking-only upstream output, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -150,7 +150,7 @@ func TestHandleNonStreamPromotesThinkingToolCallsWhenTextEmpty(t *testing.T) {
 	)
 	rec := httptest.NewRecorder()
 
-	h.handleNonStream(rec, resp, "cid-thinking-tool", "deepseek-v4-pro", "prompt", true, false, []string{"search"}, nil, nil)
+	h.handleNonStream(rec, resp, "cid-thinking-tool", "deepseek-v4-pro", "prompt", 0, true, false, []string{"search"}, nil, nil)
 	if rec.Code != http.StatusOK {
 		t.Fatalf("expected 200 for thinking tool calls, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -181,7 +181,7 @@ func TestHandleNonStreamPromotesHiddenThinkingDSMLToolCallsWhenTextEmpty(t *test
 	)
 	rec := httptest.NewRecorder()
 
-	h.handleNonStream(rec, resp, "cid-hidden-thinking-tool", "deepseek-v4-pro", "prompt", false, false, []string{"search"}, nil, nil)
+	h.handleNonStream(rec, resp, "cid-hidden-thinking-tool", "deepseek-v4-pro", "prompt", 0, false, false, []string{"search"}, nil, nil)
 	if rec.Code != http.StatusOK {
 		t.Fatalf("expected 200 for hidden thinking tool calls, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -211,7 +211,7 @@ func TestHandleStreamToolsPlainTextStreamsBeforeFinish(t *testing.T) {
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
 
-	h.handleStream(rec, req, resp, "cid6", "deepseek-v4-flash", "prompt", false, false, []string{"search"}, nil, nil)
+	h.handleStream(rec, req, resp, "cid6", "deepseek-v4-flash", "prompt", 0, false, false, []string{"search"}, nil, nil)
 
 	frames, done := parseSSEDataFrames(t, rec.Body.String())
 	if !done {
@@ -248,7 +248,7 @@ func TestHandleStreamIncompleteCapturedToolJSONFlushesAsTextOnFinalize(t *testin
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
 
-	h.handleStream(rec, req, resp, "cid10", "deepseek-v4-flash", "prompt", false, false, []string{"search"}, nil, nil)
+	h.handleStream(rec, req, resp, "cid10", "deepseek-v4-flash", "prompt", 0, false, false, []string{"search"}, nil, nil)
 
 	frames, done := parseSSEDataFrames(t, rec.Body.String())
 	if !done {
@@ -282,7 +282,7 @@ func TestHandleStreamPromotesThinkingToolCallsOnFinalizeWithoutMidstreamIntercep
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
 
-	h.handleStream(rec, req, resp, "cid-thinking-stream", "deepseek-v4-pro", "prompt", true, false, []string{"search"}, nil, nil)
+	h.handleStream(rec, req, resp, "cid-thinking-stream", "deepseek-v4-pro", "prompt", 0, true, false, []string{"search"}, nil, nil)
 
 	frames, done := parseSSEDataFrames(t, rec.Body.String())
 	if !done {
@@ -291,20 +291,16 @@ func TestHandleStreamPromotesThinkingToolCallsOnFinalizeWithoutMidstreamIntercep
 	if !streamHasToolCallsDelta(frames) {
 		t.Fatalf("expected tool_calls delta from finalize fallback, body=%s", rec.Body.String())
 	}
-	reasoningSeen := false
 	for _, frame := range frames {
 		choices, _ := frame["choices"].([]any)
 		for _, item := range choices {
 			choice, _ := item.(map[string]any)
 			delta, _ := choice["delta"].(map[string]any)
 			if asString(delta["reasoning_content"]) != "" {
-				reasoningSeen = true
+				t.Fatalf("did not expect leaked reasoning_content markup, body=%s", rec.Body.String())
 			}
 		}
 	}
-	if !reasoningSeen {
-		t.Fatalf("expected reasoning_content to stream before finalize fallback, body=%s", rec.Body.String())
-	}
 	if streamFinishReason(frames) != "tool_calls" {
 		t.Fatalf("expected finish_reason=tool_calls, body=%s", rec.Body.String())
 	}
@@ -319,7 +315,7 @@ func TestHandleStreamPromotesHiddenThinkingDSMLToolCallsOnFinalize(t *testing.T)
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
 
-	h.handleStream(rec, req, resp, "cid-hidden-thinking-stream", "deepseek-v4-pro", "prompt", false, false, []string{"search"}, nil, nil)
+	h.handleStream(rec, req, resp, "cid-hidden-thinking-stream", "deepseek-v4-pro", "prompt", 0, false, false, []string{"search"}, nil, nil)
 
 	frames, done := parseSSEDataFrames(t, rec.Body.String())
 	if !done {
@@ -353,7 +349,7 @@ func TestHandleStreamEmitsDistinctToolCallIDsAcrossSeparateToolBlocks(t *testing
 	rec := httptest.NewRecorder()
 	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", nil)
 
-	h.handleStream(rec, req, resp, "cid-multi", "deepseek-v4-flash", "prompt", false, false, []string{"read_file", "search"}, nil, nil)
+	h.handleStream(rec, req, resp, "cid-multi", "deepseek-v4-flash", "prompt", 0, false, false, []string{"read_file", "search"}, nil, nil)
 
 	frames, done := parseSSEDataFrames(t, rec.Body.String())
 	if !done {
@@ -419,7 +415,7 @@ func TestHandleStreamCoercesSchemaDeclaredStringArgumentsOnFinalize(t *testing.T
 		},
 	}
 
-	h.handleStream(rec, req, resp, "cid-string-protect", "deepseek-v4-flash", "prompt", false, false, []string{"Write"}, toolsRaw, nil)
+	h.handleStream(rec, req, resp, "cid-string-protect", "deepseek-v4-flash", "prompt", 0, false, false, []string{"Write"}, toolsRaw, nil)
 
 	frames, done := parseSSEDataFrames(t, rec.Body.String())
 	if !done {

internal/httpapi/openai/chat/ref_file_tokens.go

@@ -0,0 +1,26 @@
+package chat
+
+// addRefFileTokensToUsage adds inline-uploaded file token estimates to an existing
+// usage map inside a response object. This keeps the token accounting aware of file
+// content that the upstream model processes but that is not part of the prompt text.
+func addRefFileTokensToUsage(obj map[string]any, refFileTokens int) {
+	if refFileTokens <= 0 || obj == nil {
+		return
+	}
+	usage, ok := obj["usage"].(map[string]any)
+	if !ok || usage == nil {
+		return
+	}
+	for _, key := range []string{"input_tokens", "prompt_tokens"} {
+		if v, ok := usage[key]; ok {
+			if n, ok := v.(int); ok {
+				usage[key] = n + refFileTokens
+			}
+		}
+	}
+	if v, ok := usage["total_tokens"]; ok {
+		if n, ok := v.(int); ok {
+			usage["total_tokens"] = n + refFileTokens
+		}
+	}
+}

internal/httpapi/openai/citation_links_test.go

@@ -26,3 +26,59 @@ func TestReplaceCitationMarkersWithLinksKeepsUnknownIndex(t *testing.T) {
 		t.Fatalf("expected %q, got %q", want, got)
 	}
 }
+
+func TestReplaceCitationMarkersWithLinksSupportsReferenceMarker(t *testing.T) {
+	raw := "新闻摘要[reference:1]，详情[reference:2]。"
+	links := map[int]string{
+		1: "https://example.com/r1",
+		2: "https://example.com/r2",
+	}
+
+	got := replaceCitationMarkersWithLinks(raw, links)
+	want := "新闻摘要[1](https://example.com/r1)，详情[2](https://example.com/r2)。"
+	if got != want {
+		t.Fatalf("expected %q, got %q", want, got)
+	}
+}
+
+func TestReplaceCitationMarkersWithLinksSupportsReferenceZeroBased(t *testing.T) {
+	raw := "来源[reference:0] 与 [reference:1]。"
+	links := map[int]string{
+		1: "https://example.com/first",
+		2: "https://example.com/second",
+	}
+
+	got := replaceCitationMarkersWithLinks(raw, links)
+	want := "来源[0](https://example.com/first) 与 [1](https://example.com/second)。"
+	if got != want {
+		t.Fatalf("expected %q, got %q", want, got)
+	}
+}
+
+func TestReplaceCitationMarkersWithLinksKeepsCitationOneBasedWithZeroBasedReference(t *testing.T) {
+	raw := "引用[citation:1]，来源[reference:0]，后续[reference:1]。"
+	links := map[int]string{
+		1: "https://example.com/first",
+		2: "https://example.com/second",
+	}
+
+	got := replaceCitationMarkersWithLinks(raw, links)
+	want := "引用[1](https://example.com/first)，来源[0](https://example.com/first)，后续[1](https://example.com/second)。"
+	if got != want {
+		t.Fatalf("expected %q, got %q", want, got)
+	}
+}
+
+func TestReplaceCitationMarkersWithLinksDetectsSpacedReferenceZeroBased(t *testing.T) {
+	raw := "来源[reference: 0] 与 [reference: 1]。"
+	links := map[int]string{
+		1: "https://example.com/first",
+		2: "https://example.com/second",
+	}
+
+	got := replaceCitationMarkersWithLinks(raw, links)
+	want := "来源[0](https://example.com/first) 与 [1](https://example.com/second)。"
+	if got != want {
+		t.Fatalf("expected %q, got %q", want, got)
+	}
+}

internal/httpapi/openai/file_inline_upload_test.go

@@ -216,6 +216,45 @@ func TestChatCompletionsInlineUploadFailureReturnsBadRequest(t *testing.T) {
 	}
 }
 
+func TestChatCompletionsInlineUploadLimitReturnsBadRequest(t *testing.T) {
+	ds := &inlineUploadDSStub{}
+	h := &openAITestSurface{Store: mockOpenAIConfig{wideInput: true}, Auth: streamStatusAuthStub{}, DS: ds}
+	content := []any{map[string]any{"type": "input_text", "text": "hi"}}
+	for i := 0; i < 51; i++ {
+		content = append(content, map[string]any{
+			"type":      "image_url",
+			"image_url": map[string]any{"url": "data:image/png;base64,QUJDRA=="},
+		})
+	}
+	body, err := json.Marshal(map[string]any{
+		"model": "deepseek-v4-flash",
+		"messages": []any{map[string]any{
+			"role":    "user",
+			"content": content,
+		}},
+		"stream": false,
+	})
+	if err != nil {
+		t.Fatalf("marshal request: %v", err)
+	}
+	req := httptest.NewRequest(http.MethodPost, "/v1/chat/completions", strings.NewReader(string(body)))
+	req.Header.Set("Authorization", "Bearer direct-token")
+	req.Header.Set("Content-Type", "application/json")
+	rec := httptest.NewRecorder()
+
+	h.ChatCompletions(rec, req)
+
+	if rec.Code != http.StatusBadRequest {
+		t.Fatalf("expected 400, got %d body=%s", rec.Code, rec.Body.String())
+	}
+	if !strings.Contains(rec.Body.String(), "exceeded maximum of 50 inline files per request") {
+		t.Fatalf("expected inline file limit error, got body=%s", rec.Body.String())
+	}
+	if ds.completionReq != nil {
+		t.Fatalf("did not expect completion call after inline file limit error")
+	}
+}
+
 func TestResponsesInlineUploadFailureReturnsInternalServerError(t *testing.T) {
 	ds := &inlineUploadDSStub{uploadErr: errors.New("boom")}
 	h := &openAITestSurface{Store: mockOpenAIConfig{wideInput: true}, Auth: streamStatusAuthStub{}, DS: ds}

internal/httpapi/openai/files/file_inline_upload.go

@@ -39,11 +39,12 @@ func (e *inlineFileUploadError) Error() string {
 }
 
 type inlineUploadState struct {
-	ctx          context.Context
-	handler      *Handler
-	auth         *auth.RequestAuth
-	uploadedByID map[string]string
-	uploadCount  int
+	ctx             context.Context
+	handler         *Handler
+	auth            *auth.RequestAuth
+	uploadedByID    map[string]string
+	uploadCount     int
+	inlineFileBytes int
 }
 
 type inlineDecodedFile struct {
@@ -75,6 +76,9 @@ func (h *Handler) PreprocessInlineFileInputs(ctx context.Context, a *auth.Reques
 	if refIDs := promptcompat.CollectOpenAIRefFileIDs(req); len(refIDs) > 0 {
 		req["ref_file_ids"] = stringsToAnySlice(refIDs)
 	}
+	if state.inlineFileBytes > 0 {
+		req["_inline_file_bytes"] = state.inlineFileBytes
+	}
 	return nil
 }
 
@@ -135,13 +139,15 @@ func (s *inlineUploadState) tryUploadBlock(block map[string]any) (map[string]any
 		return nil, false, nil
 	}
 	if s.uploadCount >= maxInlineFilesPerRequest {
-		return nil, true, fmt.Errorf("exceeded maximum of %d inline files per request", maxInlineFilesPerRequest)
+		err := fmt.Errorf("exceeded maximum of %d inline files per request", maxInlineFilesPerRequest)
+		return nil, true, &inlineFileUploadError{status: http.StatusBadRequest, message: err.Error(), err: err}
 	}
 	fileID, err := s.uploadInlineFile(decoded)
 	if err != nil {
 		return nil, true, &inlineFileUploadError{status: http.StatusInternalServerError, message: "Failed to upload inline file.", err: err}
 	}
 	s.uploadCount++
+	s.inlineFileBytes += len(decoded.Data)
 	replacement := map[string]any{
 		"type":    decoded.ReplacementType,
 		"file_id": fileID,

internal/httpapi/openai/history/current_input_file.go

@@ -13,7 +13,7 @@ import (
 )
 
 const (
-	currentInputFilename    = "IGNORE.txt"
+	currentInputFilename    = promptcompat.CurrentInputContextFilename
 	currentInputContentType = "text/plain; charset=utf-8"
 	currentInputPurpose     = "assistants"
 )
@@ -35,7 +35,6 @@ func (s Service) ApplyCurrentInputFile(ctx context.Context, a *auth.RequestAuth,
 	if strings.TrimSpace(fileText) == "" {
 		return stdReq, errors.New("current user input file produced empty transcript")
 	}
-
 	result, err := s.DS.UploadFile(ctx, a, dsclient.UploadFileRequest{
 		Filename:    currentInputFilename,
 		ContentType: currentInputContentType,
@@ -58,9 +57,13 @@ func (s Service) ApplyCurrentInputFile(ctx context.Context, a *auth.RequestAuth,
 	}
 
 	stdReq.Messages = messages
+	stdReq.HistoryText = fileText
 	stdReq.CurrentInputFileApplied = true
 	stdReq.RefFileIDs = prependUniqueRefFileID(stdReq.RefFileIDs, fileID)
 	stdReq.FinalPrompt, stdReq.ToolNames = promptcompat.BuildOpenAIPrompt(messages, stdReq.ToolsRaw, "", stdReq.ToolChoice, stdReq.Thinking)
+	// Token accounting must reflect the actual downstream context:
+	// the uploaded history.txt file content + the neutral live prompt.
+	stdReq.PromptTokenText = fileText + "\n" + stdReq.FinalPrompt
 	return stdReq, nil
 }
 

internal/httpapi/openai/history_split_test.go

@@ -14,6 +14,7 @@ import (
 	"ds2api/internal/auth"
 	dsclient "ds2api/internal/deepseek/client"
 	"ds2api/internal/promptcompat"
+	"ds2api/internal/util"
 )
 
 func historySplitTestMessages() []any {
@@ -64,8 +65,8 @@ func TestBuildOpenAICurrentInputContextTranscriptUsesInjectedFileWrapper(t *test
 	_, historyMessages := splitOpenAIHistoryMessages(historySplitTestMessages(), 1)
 	transcript := buildOpenAICurrentInputContextTranscript(historyMessages)
 
-	if !strings.HasPrefix(transcript, "[file content end]\n\n") {
-		t.Fatalf("expected injected file wrapper prefix, got %q", transcript)
+	if strings.Contains(transcript, "[file content end]") || strings.Contains(transcript, "[file content begin]") || strings.Contains(transcript, "[file name]:") {
+		t.Fatalf("expected plain transcript without file wrapper tags, got %q", transcript)
 	}
 	if !strings.Contains(transcript, "<｜begin▁of▁sentence｜>") {
 		t.Fatalf("expected serialized conversation markers, got %q", transcript)
@@ -79,9 +80,7 @@ func TestBuildOpenAICurrentInputContextTranscriptUsesInjectedFileWrapper(t *test
 	if !strings.Contains(transcript, "<|DSML|tool_calls>") {
 		t.Fatalf("expected tool calls preserved, got %q", transcript)
 	}
-	if !strings.HasSuffix(transcript, "\n[file name]: IGNORE\n[file content begin]\n") {
-		t.Fatalf("expected injected file wrapper suffix, got %q", transcript)
-	}
+
 }
 
 func TestSplitOpenAIHistoryMessagesUsesLatestUserTurn(t *testing.T) {
@@ -274,12 +273,12 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T)
 		t.Fatalf("expected 1 current input upload, got %d", len(ds.uploadCalls))
 	}
 	upload := ds.uploadCalls[0]
-	if upload.Filename != "IGNORE.txt" {
+	if upload.Filename != "history.txt" {
 		t.Fatalf("unexpected upload filename: %q", upload.Filename)
 	}
 	uploadedText := string(upload.Data)
-	if !strings.HasPrefix(uploadedText, "[file content end]\n\n") {
-		t.Fatalf("expected injected file wrapper prefix, got %q", uploadedText)
+	if strings.Contains(uploadedText, "[file content end]") || strings.Contains(uploadedText, "[file content begin]") || strings.Contains(uploadedText, "[file name]:") {
+		t.Fatalf("expected uploaded transcript without file wrapper tags, got %q", uploadedText)
 	}
 	if !strings.Contains(uploadedText, "<｜begin▁of▁sentence｜><｜User｜>first turn content that is long enough") {
 		t.Fatalf("expected serialized current user turn markers, got %q", uploadedText)
@@ -287,13 +286,11 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T)
 	if !strings.Contains(uploadedText, promptcompat.ThinkingInjectionMarker) {
 		t.Fatalf("expected thinking injection in current input file, got %q", uploadedText)
 	}
-	if !strings.HasSuffix(uploadedText, "\n[file name]: IGNORE\n[file content begin]\n") {
-		t.Fatalf("expected injected file wrapper suffix, got %q", uploadedText)
-	}
+
 	if strings.Contains(out.FinalPrompt, "first turn content that is long enough") {
 		t.Fatalf("expected current input text to be replaced in live prompt, got %s", out.FinalPrompt)
 	}
-	if strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "IGNORE.txt") || strings.Contains(out.FinalPrompt, "Read that file") {
+	if strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "history.txt") || strings.Contains(out.FinalPrompt, "Read that file") {
 		t.Fatalf("expected live prompt not to instruct file reads, got %s", out.FinalPrompt)
 	}
 	if !strings.Contains(out.FinalPrompt, "Answer the latest user request directly.") {
@@ -302,6 +299,52 @@ func TestApplyCurrentInputFileUploadsFirstTurnWithInjectedWrapper(t *testing.T)
 	if len(out.RefFileIDs) != 1 || out.RefFileIDs[0] != "file-inline-1" {
 		t.Fatalf("expected current input file id in ref_file_ids, got %#v", out.RefFileIDs)
 	}
+	if !strings.Contains(out.PromptTokenText, "first turn content that is long enough") {
+		t.Fatalf("expected prompt token text to preserve original full context, got %q", out.PromptTokenText)
+	}
+}
+
+func TestApplyCurrentInputFilePreservesFullContextPromptForTokenCounting(t *testing.T) {
+	ds := &inlineUploadDSStub{}
+	h := &openAITestSurface{
+		Store: mockOpenAIConfig{
+			wideInput:           true,
+			currentInputEnabled: true,
+			currentInputMin:     0,
+			thinkingInjection:   boolPtr(true),
+		},
+		DS: ds,
+	}
+	req := map[string]any{
+		"model":    "deepseek-v4-flash",
+		"messages": historySplitTestMessages(),
+	}
+	stdReq, err := promptcompat.NormalizeOpenAIChatRequest(h.Store, req, "")
+	if err != nil {
+		t.Fatalf("normalize failed: %v", err)
+	}
+
+	out, err := h.applyCurrentInputFile(context.Background(), &auth.RequestAuth{DeepSeekToken: "token"}, stdReq)
+	if err != nil {
+		t.Fatalf("apply current input file failed: %v", err)
+	}
+	if out.FinalPrompt == stdReq.FinalPrompt {
+		t.Fatalf("expected live prompt to be rewritten after current input file")
+	}
+	// PromptTokenText must include the uploaded file content (which contains the full context)
+	// plus the neutral live prompt — reflecting the actual downstream token cost.
+	if !strings.Contains(out.PromptTokenText, "first user turn") || !strings.Contains(out.PromptTokenText, "latest user turn") {
+		t.Fatalf("expected prompt token text to contain file context with full conversation, got %q", out.PromptTokenText)
+	}
+	if strings.Contains(out.PromptTokenText, "[file content end]") || strings.Contains(out.PromptTokenText, "[file name]:") {
+		t.Fatalf("expected prompt token text to use raw transcript without wrapper tags, got %q", out.PromptTokenText)
+	}
+	if !strings.Contains(out.PromptTokenText, "Answer the latest user request directly.") {
+		t.Fatalf("expected prompt token text to also include neutral live prompt, got %q", out.PromptTokenText)
+	}
+	if strings.Contains(out.FinalPrompt, "first user turn") || strings.Contains(out.FinalPrompt, "latest user turn") {
+		t.Fatalf("expected live prompt to hide original turns, got %q", out.FinalPrompt)
+	}
 }
 
 func TestApplyCurrentInputFileUploadsFullContextFile(t *testing.T) {
@@ -335,8 +378,8 @@ func TestApplyCurrentInputFileUploadsFullContextFile(t *testing.T) {
 		t.Fatalf("expected one current input upload, got %d", len(ds.uploadCalls))
 	}
 	upload := ds.uploadCalls[0]
-	if upload.Filename != "IGNORE.txt" {
-		t.Fatalf("expected IGNORE.txt upload, got %q", upload.Filename)
+	if upload.Filename != "history.txt" {
+		t.Fatalf("expected history.txt upload, got %q", upload.Filename)
 	}
 	uploadedText := string(upload.Data)
 	for _, want := range []string{"system instructions", "first user turn", "hidden reasoning", "tool result", "latest user turn", promptcompat.ThinkingInjectionMarker} {
@@ -344,7 +387,7 @@ func TestApplyCurrentInputFileUploadsFullContextFile(t *testing.T) {
 			t.Fatalf("expected full context file to contain %q, got %q", want, uploadedText)
 		}
 	}
-	if strings.Contains(out.FinalPrompt, "first user turn") || strings.Contains(out.FinalPrompt, "latest user turn") || strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "IGNORE.txt") || strings.Contains(out.FinalPrompt, "Read that file") {
+	if strings.Contains(out.FinalPrompt, "first user turn") || strings.Contains(out.FinalPrompt, "latest user turn") || strings.Contains(out.FinalPrompt, "CURRENT_USER_INPUT.txt") || strings.Contains(out.FinalPrompt, "history.txt") || strings.Contains(out.FinalPrompt, "Read that file") {
 		t.Fatalf("expected live prompt to use only a neutral continuation instruction, got %s", out.FinalPrompt)
 	}
 	if !strings.Contains(out.FinalPrompt, "Answer the latest user request directly.") {
@@ -352,7 +395,7 @@ func TestApplyCurrentInputFileUploadsFullContextFile(t *testing.T) {
 	}
 }
 
-func TestApplyCurrentInputFileLeavesHistoryTextEmpty(t *testing.T) {
+func TestApplyCurrentInputFileCarriesHistoryText(t *testing.T) {
 	ds := &inlineUploadDSStub{}
 	h := &openAITestSurface{
 		Store: mockOpenAIConfig{
@@ -377,8 +420,8 @@ func TestApplyCurrentInputFileLeavesHistoryTextEmpty(t *testing.T) {
 	if len(ds.uploadCalls) != 1 {
 		t.Fatalf("expected 1 upload call, got %d", len(ds.uploadCalls))
 	}
-	if out.HistoryText != "" {
-		t.Fatalf("expected current input file flow to leave history text empty, got %q", out.HistoryText)
+	if out.HistoryText != string(ds.uploadCalls[0].Data) {
+		t.Fatalf("expected current input file flow to preserve uploaded text in history, got %q", out.HistoryText)
 	}
 }
 
@@ -411,15 +454,15 @@ func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *t
 		t.Fatalf("expected 1 upload call, got %d", len(ds.uploadCalls))
 	}
 	upload := ds.uploadCalls[0]
-	if upload.Filename != "IGNORE.txt" {
+	if upload.Filename != "history.txt" {
 		t.Fatalf("unexpected upload filename: %q", upload.Filename)
 	}
 	if upload.Purpose != "assistants" {
 		t.Fatalf("unexpected purpose: %q", upload.Purpose)
 	}
 	historyText := string(upload.Data)
-	if !strings.Contains(historyText, "[file content end]") || !strings.Contains(historyText, "[file name]: IGNORE") {
-		t.Fatalf("expected injected IGNORE wrapper, got %s", historyText)
+	if strings.Contains(historyText, "[file content end]") || strings.Contains(historyText, "[file content begin]") || strings.Contains(historyText, "[file name]:") {
+		t.Fatalf("expected plain history transcript without wrapper tags, got %s", historyText)
 	}
 	if !strings.Contains(historyText, "latest user turn") {
 		t.Fatalf("expected full context to include latest turn, got %s", historyText)
@@ -438,6 +481,16 @@ func TestChatCompletionsCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *t
 	if len(refIDs) == 0 || refIDs[0] != "file-inline-1" {
 		t.Fatalf("expected uploaded current input file to be first ref_file_id, got %#v", ds.completionReq["ref_file_ids"])
 	}
+	var body map[string]any
+	if err := json.Unmarshal(rec.Body.Bytes(), &body); err != nil {
+		t.Fatalf("decode response failed: %v", err)
+	}
+	usage, _ := body["usage"].(map[string]any)
+	promptTokens := int(usage["prompt_tokens"].(float64))
+	neutralCount := util.CountPromptTokens(promptText, "deepseek-v4-flash")
+	if promptTokens <= neutralCount {
+		t.Fatalf("expected prompt_tokens to exceed neutral live prompt count (includes file context), got=%d neutral=%d", promptTokens, neutralCount)
+	}
 }
 
 func TestResponsesCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *testing.T) {
@@ -480,6 +533,16 @@ func TestResponsesCurrentInputFileUploadsContextAndKeepsNeutralPrompt(t *testing
 	if strings.Contains(promptText, "first user turn") || strings.Contains(promptText, "latest user turn") {
 		t.Fatalf("expected prompt to hide original turns, got %s", promptText)
 	}
+	var body map[string]any
+	if err := json.Unmarshal(rec.Body.Bytes(), &body); err != nil {
+		t.Fatalf("decode response failed: %v", err)
+	}
+	usage, _ := body["usage"].(map[string]any)
+	inputTokens := int(usage["input_tokens"].(float64))
+	neutralCount := util.CountPromptTokens(promptText, "deepseek-v4-flash")
+	if inputTokens <= neutralCount {
+		t.Fatalf("expected input_tokens to exceed neutral live prompt count (includes file context), got=%d neutral=%d", inputTokens, neutralCount)
+	}
 }
 
 func TestChatCompletionsCurrentInputFileMapsManagedAuthFailureTo401(t *testing.T) {

internal/httpapi/openai/leaked_output_sanitize_test.go

@@ -42,6 +42,14 @@ func TestSanitizeLeakedOutputRemovesDanglingThinkBlock(t *testing.T) {
 	}
 }
 
+func TestSanitizeLeakedOutputRemovesCompleteDSMLToolCallWrapper(t *testing.T) {
+	raw := "前置文本\n<｜DSML｜tool_calls>\n<｜DSML｜invoke name=\"Bash\">\n<｜DSML｜parameter name=\"command\"></｜DSML｜parameter>\n</｜DSML｜invoke>\n</｜DSML｜tool_calls>\n后置文本"
+	got := sanitizeLeakedOutput(raw)
+	if got != "前置文本\n\n后置文本" {
+		t.Fatalf("unexpected sanitize result for leaked dsml wrapper: %q", got)
+	}
+}
+
 func TestSanitizeLeakedOutputRemovesAgentXMLLeaks(t *testing.T) {
 	raw := "Done.<attempt_completion><result>Some final answer</result></attempt_completion>"
 	got := sanitizeLeakedOutput(raw)

internal/httpapi/openai/responses/empty_retry_runtime.go

@@ -18,6 +18,8 @@ import (
 )
 
 type responsesNonStreamResult struct {
+	rawThinking           string
+	rawText               string
 	thinking              string
 	toolDetectionThinking string
 	text                  string
@@ -27,11 +29,12 @@ type responsesNonStreamResult struct {
 	responseMessageID     int
 }
 
-func (h *Handler) handleResponsesNonStreamWithRetry(w http.ResponseWriter, ctx context.Context, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, owner, responseID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
+func (h *Handler) handleResponsesNonStreamWithRetry(w http.ResponseWriter, ctx context.Context, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, owner, responseID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
 	attempts := 0
 	currentResp := resp
 	usagePrompt := finalPrompt
 	accumulatedThinking := ""
+	accumulatedRawThinking := ""
 	accumulatedToolDetectionThinking := ""
 	for {
 		result, ok := h.collectResponsesNonStreamAttempt(w, currentResp, responseID, model, usagePrompt, thinkingEnabled, searchEnabled, toolNames, toolsRaw)
@@ -39,11 +42,16 @@ func (h *Handler) handleResponsesNonStreamWithRetry(w http.ResponseWriter, ctx c
 			return
 		}
 		accumulatedThinking += sse.TrimContinuationOverlap(accumulatedThinking, result.thinking)
+		accumulatedRawThinking += sse.TrimContinuationOverlap(accumulatedRawThinking, result.rawThinking)
 		accumulatedToolDetectionThinking += sse.TrimContinuationOverlap(accumulatedToolDetectionThinking, result.toolDetectionThinking)
 		result.thinking = accumulatedThinking
+		result.rawThinking = accumulatedRawThinking
 		result.toolDetectionThinking = accumulatedToolDetectionThinking
-		result.parsed = detectAssistantToolCalls(result.text, result.thinking, result.toolDetectionThinking, toolNames)
+		result.parsed = detectAssistantToolCalls(result.rawText, result.text, result.rawThinking, result.toolDetectionThinking, toolNames)
 		result.body = openaifmt.BuildResponseObjectWithToolCalls(responseID, model, usagePrompt, result.thinking, result.text, result.parsed.Calls, toolsRaw)
+		if refFileTokens > 0 {
+			addRefFileTokensToUsage(result.body, refFileTokens)
+		}
 
 		if !shouldRetryResponsesNonStream(result, attempts) {
 			h.finishResponsesNonStreamResult(w, result, attempts, owner, responseID, toolChoice, traceID)
@@ -63,7 +71,7 @@ func (h *Handler) handleResponsesNonStreamWithRetry(w http.ResponseWriter, ctx c
 			config.Logger.Warn("[openai_empty_retry] retry request failed", "surface", "responses", "stream", false, "retry_attempt", attempts, "error", err)
 			return
 		}
-		usagePrompt = usagePromptWithEmptyOutputRetry(finalPrompt, attempts)
+		usagePrompt = usagePromptWithEmptyOutputRetry(usagePrompt, attempts)
 		currentResp = nextResp
 	}
 }
@@ -78,16 +86,17 @@ func (h *Handler) collectResponsesNonStreamAttempt(w http.ResponseWriter, resp *
 	result := sse.CollectStream(resp, thinkingEnabled, false)
 	stripReferenceMarkers := h.compatStripReferenceMarkers()
 	sanitizedThinking := cleanVisibleOutput(result.Thinking, stripReferenceMarkers)
-	toolDetectionThinking := cleanVisibleOutput(result.ToolDetectionThinking, stripReferenceMarkers)
 	sanitizedText := cleanVisibleOutput(result.Text, stripReferenceMarkers)
 	if searchEnabled {
 		sanitizedText = replaceCitationMarkersWithLinks(sanitizedText, result.CitationLinks)
 	}
-	textParsed := detectAssistantToolCalls(sanitizedText, sanitizedThinking, toolDetectionThinking, toolNames)
+	textParsed := detectAssistantToolCalls(result.Text, sanitizedText, result.Thinking, result.ToolDetectionThinking, toolNames)
 	responseObj := openaifmt.BuildResponseObjectWithToolCalls(responseID, model, usagePrompt, sanitizedThinking, sanitizedText, textParsed.Calls, toolsRaw)
 	return responsesNonStreamResult{
+		rawThinking:           result.Thinking,
+		rawText:               result.Text,
 		thinking:              sanitizedThinking,
-		toolDetectionThinking: toolDetectionThinking,
+		toolDetectionThinking: result.ToolDetectionThinking,
 		text:                  sanitizedText,
 		contentFilter:         result.ContentFilter,
 		parsed:                textParsed,
@@ -123,8 +132,8 @@ func shouldRetryResponsesNonStream(result responsesNonStreamResult, attempts int
 		strings.TrimSpace(result.text) == ""
 }
 
-func (h *Handler) handleResponsesStreamWithRetry(w http.ResponseWriter, r *http.Request, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, owner, responseID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
-	streamRuntime, initialType, ok := h.prepareResponsesStreamRuntime(w, resp, owner, responseID, model, finalPrompt, thinkingEnabled, searchEnabled, toolNames, toolsRaw, toolChoice, traceID)
+func (h *Handler) handleResponsesStreamWithRetry(w http.ResponseWriter, r *http.Request, a *auth.RequestAuth, resp *http.Response, payload map[string]any, pow, owner, responseID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
+	streamRuntime, initialType, ok := h.prepareResponsesStreamRuntime(w, resp, owner, responseID, model, finalPrompt, refFileTokens, thinkingEnabled, searchEnabled, toolNames, toolsRaw, toolChoice, traceID)
 	if !ok {
 		return
 	}
@@ -165,7 +174,7 @@ func (h *Handler) handleResponsesStreamWithRetry(w http.ResponseWriter, r *http.
 	}
 }
 
-func (h *Handler) prepareResponsesStreamRuntime(w http.ResponseWriter, resp *http.Response, owner, responseID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) (*responsesStreamRuntime, string, bool) {
+func (h *Handler) prepareResponsesStreamRuntime(w http.ResponseWriter, resp *http.Response, owner, responseID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) (*responsesStreamRuntime, string, bool) {
 	if resp.StatusCode != http.StatusOK {
 		defer func() { _ = resp.Body.Close() }()
 		body, _ := io.ReadAll(resp.Body)
@@ -190,6 +199,7 @@ func (h *Handler) prepareResponsesStreamRuntime(w http.ResponseWriter, resp *htt
 			h.getResponseStore().put(owner, responseID, obj)
 		},
 	)
+	streamRuntime.refFileTokens = refFileTokens
 	streamRuntime.sendCreated()
 	return streamRuntime, initialType, true
 }

internal/httpapi/openai/responses/handler.go

@@ -130,6 +130,6 @@ func filterIncrementalToolCallDeltasByAllowed(deltas []toolstream.ToolCallDelta,
 	return shared.FilterIncrementalToolCallDeltasByAllowed(deltas, seenNames)
 }
 
-func detectAssistantToolCalls(text, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult {
-	return shared.DetectAssistantToolCalls(text, exposedThinking, detectionThinking, toolNames)
+func detectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult {
+	return shared.DetectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking, toolNames)
 }

internal/httpapi/openai/responses/ref_file_tokens.go

@@ -0,0 +1,26 @@
+package responses
+
+// addRefFileTokensToUsage adds inline-uploaded file token estimates to an existing
+// usage map inside a response object. This keeps the token accounting aware of file
+// content that the upstream model processes but that is not part of the prompt text.
+func addRefFileTokensToUsage(obj map[string]any, refFileTokens int) {
+	if refFileTokens <= 0 || obj == nil {
+		return
+	}
+	usage, ok := obj["usage"].(map[string]any)
+	if !ok || usage == nil {
+		return
+	}
+	for _, key := range []string{"input_tokens", "prompt_tokens"} {
+		if v, ok := usage[key]; ok {
+			if n, ok := v.(int); ok {
+				usage[key] = n + refFileTokens
+			}
+		}
+	}
+	if v, ok := usage["total_tokens"]; ok {
+		if n, ok := v.(int); ok {
+			usage["total_tokens"] = n + refFileTokens
+		}
+	}
+}

internal/httpapi/openai/responses/responses_handler.go

@@ -114,14 +114,15 @@ func (h *Handler) Responses(w http.ResponseWriter, r *http.Request) {
 	}
 
 	responseID := "resp_" + strings.ReplaceAll(uuid.NewString(), "-", "")
+	refFileTokens := stdReq.RefFileTokens
 	if stdReq.Stream {
-		h.handleResponsesStreamWithRetry(w, r, a, resp, payload, pow, owner, responseID, stdReq.ResponseModel, stdReq.FinalPrompt, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, stdReq.ToolChoice, traceID)
+		h.handleResponsesStreamWithRetry(w, r, a, resp, payload, pow, owner, responseID, stdReq.ResponseModel, stdReq.PromptTokenText, refFileTokens, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, stdReq.ToolChoice, traceID)
 		return
 	}
-	h.handleResponsesNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, owner, responseID, stdReq.ResponseModel, stdReq.FinalPrompt, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, stdReq.ToolChoice, traceID)
+	h.handleResponsesNonStreamWithRetry(w, r.Context(), a, resp, payload, pow, owner, responseID, stdReq.ResponseModel, stdReq.PromptTokenText, refFileTokens, stdReq.Thinking, stdReq.Search, stdReq.ToolNames, stdReq.ToolsRaw, stdReq.ToolChoice, traceID)
 }
 
-func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Response, owner, responseID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
+func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Response, owner, responseID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
@@ -131,12 +132,11 @@ func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Res
 	result := sse.CollectStream(resp, thinkingEnabled, true)
 	stripReferenceMarkers := h.compatStripReferenceMarkers()
 	sanitizedThinking := cleanVisibleOutput(result.Thinking, stripReferenceMarkers)
-	toolDetectionThinking := cleanVisibleOutput(result.ToolDetectionThinking, stripReferenceMarkers)
 	sanitizedText := cleanVisibleOutput(result.Text, stripReferenceMarkers)
 	if searchEnabled {
 		sanitizedText = replaceCitationMarkersWithLinks(sanitizedText, result.CitationLinks)
 	}
-	textParsed := detectAssistantToolCalls(sanitizedText, sanitizedThinking, toolDetectionThinking, toolNames)
+	textParsed := detectAssistantToolCalls(result.Text, sanitizedText, result.Thinking, result.ToolDetectionThinking, toolNames)
 	if len(textParsed.Calls) == 0 && writeUpstreamEmptyOutputError(w, sanitizedText, sanitizedThinking, result.ContentFilter) {
 		return
 	}
@@ -149,11 +149,14 @@ func (h *Handler) handleResponsesNonStream(w http.ResponseWriter, resp *http.Res
 	}
 
 	responseObj := openaifmt.BuildResponseObjectWithToolCalls(responseID, model, finalPrompt, sanitizedThinking, sanitizedText, textParsed.Calls, toolsRaw)
+	if refFileTokens > 0 {
+		addRefFileTokensToUsage(responseObj, refFileTokens)
+	}
 	h.getResponseStore().put(owner, responseID, responseObj)
 	writeJSON(w, http.StatusOK, responseObj)
 }
 
-func (h *Handler) handleResponsesStream(w http.ResponseWriter, r *http.Request, resp *http.Response, owner, responseID, model, finalPrompt string, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
+func (h *Handler) handleResponsesStream(w http.ResponseWriter, r *http.Request, resp *http.Response, owner, responseID, model, finalPrompt string, refFileTokens int, thinkingEnabled, searchEnabled bool, toolNames []string, toolsRaw any, toolChoice promptcompat.ToolChoicePolicy, traceID string) {
 	defer func() { _ = resp.Body.Close() }()
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
@@ -195,6 +198,7 @@ func (h *Handler) handleResponsesStream(w http.ResponseWriter, r *http.Request,
 			h.getResponseStore().put(owner, responseID, obj)
 		},
 	)
+	streamRuntime.refFileTokens = refFileTokens
 	streamRuntime.sendCreated()
 
 	streamengine.ConsumeSSE(streamengine.ConsumeConfig{

internal/httpapi/openai/responses/responses_stream_runtime_core.go

@@ -18,13 +18,14 @@ type responsesStreamRuntime struct {
 	rc       *http.ResponseController
 	canFlush bool
 
-	responseID  string
-	model       string
-	finalPrompt string
-	toolNames   []string
-	toolsRaw    any
-	traceID     string
-	toolChoice  promptcompat.ToolChoicePolicy
+	responseID    string
+	model         string
+	finalPrompt   string
+	refFileTokens int
+	toolNames     []string
+	toolsRaw      any
+	traceID       string
+	toolChoice    promptcompat.ToolChoicePolicy
 
 	thinkingEnabled       bool
 	searchEnabled         bool
@@ -36,8 +37,10 @@ type responsesStreamRuntime struct {
 	toolCallsDoneEmitted bool
 
 	sieve                 toolstream.State
+	rawThinking           strings.Builder
 	thinking              strings.Builder
 	toolDetectionThinking strings.Builder
+	rawText               strings.Builder
 	text                  strings.Builder
 	visibleText           strings.Builder
 	responseMessageID     int
@@ -141,15 +144,14 @@ func (s *responsesStreamRuntime) finalize(finishReason string, deferEmptyOutput
 	s.finalErrorStatus = 0
 	s.finalErrorMessage = ""
 	s.finalErrorCode = ""
-	finalThinking := s.thinking.String()
-	finalToolDetectionThinking := s.toolDetectionThinking.String()
-	finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers)
-
 	if s.bufferToolContent {
 		s.processToolStreamEvents(toolstream.Flush(&s.sieve, s.toolNames), true, true)
 	}
 
-	textParsed := detectAssistantToolCalls(finalText, finalThinking, finalToolDetectionThinking, s.toolNames)
+	finalThinking := s.thinking.String()
+	finalToolDetectionThinking := s.toolDetectionThinking.String()
+	finalText := cleanVisibleOutput(s.text.String(), s.stripReferenceMarkers)
+	textParsed := detectAssistantToolCalls(s.rawText.String(), finalText, s.rawThinking.String(), finalToolDetectionThinking, s.toolNames)
 	detected := textParsed.Calls
 	s.logToolPolicyRejections(textParsed)
 
@@ -227,18 +229,19 @@ func (s *responsesStreamRuntime) onParsed(parsed sse.LineResult) streamengine.Pa
 		}
 	}
 	for _, p := range parsed.Parts {
-		cleanedText := cleanVisibleOutput(p.Text, s.stripReferenceMarkers)
-		if cleanedText == "" {
-			continue
-		}
-		if p.Type != "thinking" && s.searchEnabled && sse.IsCitation(cleanedText) {
-			continue
-		}
-		contentSeen = true
 		if p.Type == "thinking" {
+			rawTrimmed := sse.TrimContinuationOverlap(s.rawThinking.String(), p.Text)
+			if rawTrimmed != "" {
+				s.rawThinking.WriteString(rawTrimmed)
+				contentSeen = true
+			}
 			if !s.thinkingEnabled {
 				continue
 			}
+			cleanedText := cleanVisibleOutput(rawTrimmed, s.stripReferenceMarkers)
+			if cleanedText == "" {
+				continue
+			}
 			trimmed := sse.TrimContinuationOverlap(s.thinking.String(), cleanedText)
 			if trimmed == "" {
 				continue
@@ -248,16 +251,28 @@ func (s *responsesStreamRuntime) onParsed(parsed sse.LineResult) streamengine.Pa
 			continue
 		}
 
-		trimmed := sse.TrimContinuationOverlap(s.text.String(), cleanedText)
-		if trimmed == "" {
+		rawTrimmed := sse.TrimContinuationOverlap(s.rawText.String(), p.Text)
+		if rawTrimmed == "" {
 			continue
 		}
-		s.text.WriteString(trimmed)
+		s.rawText.WriteString(rawTrimmed)
+		contentSeen = true
+		cleanedText := cleanVisibleOutput(rawTrimmed, s.stripReferenceMarkers)
+		if s.searchEnabled && sse.IsCitation(cleanedText) {
+			continue
+		}
+		trimmed := sse.TrimContinuationOverlap(s.text.String(), cleanedText)
+		if trimmed != "" {
+			s.text.WriteString(trimmed)
+		}
 		if !s.bufferToolContent {
+			if trimmed == "" {
+				continue
+			}
 			s.emitTextDelta(trimmed)
 			continue
 		}
-		s.processToolStreamEvents(toolstream.ProcessChunk(&s.sieve, trimmed, s.toolNames), true, true)
+		s.processToolStreamEvents(toolstream.ProcessChunk(&s.sieve, rawTrimmed, s.toolNames), true, true)
 	}
 
 	return streamengine.ParsedDecision{ContentSeen: contentSeen}

internal/httpapi/openai/responses/responses_stream_runtime_events.go

@@ -4,6 +4,7 @@ import (
 	"encoding/json"
 
 	openaifmt "ds2api/internal/format/openai"
+	"ds2api/internal/sse"
 	"ds2api/internal/toolstream"
 )
 
@@ -43,7 +44,10 @@ func (s *responsesStreamRuntime) sendDone() {
 func (s *responsesStreamRuntime) processToolStreamEvents(events []toolstream.Event, emitContent bool, resetAfterToolCalls bool) {
 	for _, evt := range events {
 		if emitContent && evt.Content != "" {
-			s.emitTextDelta(evt.Content)
+			cleaned := cleanVisibleOutput(evt.Content, s.stripReferenceMarkers)
+			if cleaned != "" && (!s.searchEnabled || !sse.IsCitation(cleaned)) {
+				s.emitTextDelta(cleaned)
+			}
 		}
 		if len(evt.ToolCallDeltas) > 0 {
 			if !s.emitEarlyToolDeltas {

internal/httpapi/openai/responses/responses_stream_runtime_toolcalls_finalize.go

@@ -145,7 +145,7 @@ func (s *responsesStreamRuntime) buildCompletedResponseObject(finalThinking, fin
 		}
 	}
 
-	return openaifmt.BuildResponseObjectFromItems(
+	obj := openaifmt.BuildResponseObjectFromItems(
 		s.responseID,
 		s.model,
 		s.finalPrompt,
@@ -154,4 +154,8 @@ func (s *responsesStreamRuntime) buildCompletedResponseObject(finalThinking, fin
 		output,
 		outputText,
 	)
+	if s.refFileTokens > 0 {
+		addRefFileTokensToUsage(obj, s.refFileTokens)
+	}
+	return obj
 }

internal/httpapi/openai/responses/responses_stream_test.go

@@ -27,7 +27,7 @@ func TestHandleResponsesStreamDoesNotEmitReasoningTextCompatEvents(t *testing.T)
 		Body:       io.NopCloser(strings.NewReader(streamBody)),
 	}
 
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", true, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", 0, true, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
 
 	body := rec.Body.String()
 	if !strings.Contains(body, "event: response.reasoning.delta") {
@@ -57,7 +57,7 @@ func TestHandleResponsesStreamEmitsOutputTextDoneBeforeContentPartDone(t *testin
 		Body:       io.NopCloser(strings.NewReader(streamBody)),
 	}
 
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
 	body := rec.Body.String()
 	if !strings.Contains(body, "event: response.output_text.done") {
 		t.Fatalf("expected response.output_text.done payload, body=%s", body)
@@ -91,7 +91,7 @@ func TestHandleResponsesStreamOutputTextDeltaCarriesItemIndexes(t *testing.T) {
 		Body:       io.NopCloser(strings.NewReader(streamBody)),
 	}
 
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
 	body := rec.Body.String()
 
 	deltaPayload, ok := extractSSEEventPayload(body, "response.output_text.delta")
@@ -130,7 +130,7 @@ func TestHandleResponsesStreamEmitsDistinctToolCallIDsAcrossSeparateToolBlocks(t
 		Body:       io.NopCloser(strings.NewReader(streamBody)),
 	}
 
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", false, false, []string{"read_file", "search"}, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, false, false, []string{"read_file", "search"}, nil, promptcompat.DefaultToolChoicePolicy(), "")
 
 	body := rec.Body.String()
 	doneEvents := extractSSEEventPayloads(body, "response.function_call_arguments.done")
@@ -183,7 +183,7 @@ func TestHandleResponsesStreamRequiredToolChoiceFailure(t *testing.T) {
 		Mode:    promptcompat.ToolChoiceRequired,
 		Allowed: map[string]struct{}{"read_file": {}},
 	}
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", false, false, []string{"read_file"}, nil, policy, "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, false, false, []string{"read_file"}, nil, policy, "")
 
 	body := rec.Body.String()
 	if !strings.Contains(body, "event: response.failed") {
@@ -213,7 +213,7 @@ func TestHandleResponsesStreamFailsWhenUpstreamHasOnlyThinking(t *testing.T) {
 		Body:       io.NopCloser(strings.NewReader(streamBody)),
 	}
 
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", true, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", 0, true, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
 
 	body := rec.Body.String()
 	if !strings.Contains(body, "event: response.failed") {
@@ -251,11 +251,11 @@ func TestHandleResponsesStreamPromotesThinkingToolCallsOnFinalizeWithoutMidstrea
 		Body:       io.NopCloser(strings.NewReader(streamBody)),
 	}
 
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", true, false, []string{"read_file"}, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", 0, true, false, []string{"read_file"}, nil, promptcompat.DefaultToolChoicePolicy(), "")
 
 	body := rec.Body.String()
-	if !strings.Contains(body, "event: response.reasoning.delta") {
-		t.Fatalf("expected reasoning delta in stream body, got %s", body)
+	if strings.Contains(body, "event: response.reasoning.delta") {
+		t.Fatalf("did not expect leaked reasoning delta in stream body, got %s", body)
 	}
 	if !strings.Contains(body, "event: response.function_call_arguments.done") {
 		t.Fatalf("expected finalize fallback function call event, got %s", body)
@@ -288,7 +288,7 @@ func TestHandleResponsesStreamPromotesHiddenThinkingDSMLToolCallsOnFinalize(t *t
 		Mode:    promptcompat.ToolChoiceRequired,
 		Allowed: map[string]struct{}{"read_file": {}},
 	}
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_hidden", "deepseek-v4-pro", "prompt", false, false, []string{"read_file"}, nil, policy, "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_hidden", "deepseek-v4-pro", "prompt", 0, false, false, []string{"read_file"}, nil, policy, "")
 
 	body := rec.Body.String()
 	if strings.Contains(body, "event: response.reasoning.delta") {
@@ -317,7 +317,7 @@ func TestHandleResponsesNonStreamRequiredToolChoiceViolation(t *testing.T) {
 		Allowed: map[string]struct{}{"read_file": {}},
 	}
 
-	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", false, false, []string{"read_file"}, nil, policy, "")
+	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, false, false, []string{"read_file"}, nil, policy, "")
 	if rec.Code != http.StatusUnprocessableEntity {
 		t.Fatalf("expected 422 for required tool_choice violation, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -344,7 +344,7 @@ func TestHandleResponsesNonStreamRequiredToolChoiceIgnoresThinkingToolPayloadWhe
 		Allowed: map[string]struct{}{"read_file": {}},
 	}
 
-	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", true, false, []string{"read_file"}, nil, policy, "")
+	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, true, false, []string{"read_file"}, nil, policy, "")
 	if rec.Code != http.StatusUnprocessableEntity {
 		t.Fatalf("expected 422 for required tool_choice violation, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -366,7 +366,7 @@ func TestHandleResponsesNonStreamReturns429WhenUpstreamOutputEmpty(t *testing.T)
 		)),
 	}
 
-	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
 	if rec.Code != http.StatusTooManyRequests {
 		t.Fatalf("expected 429 for empty upstream output, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -388,7 +388,7 @@ func TestHandleResponsesNonStreamReturnsContentFilterErrorWhenUpstreamFilteredWi
 		)),
 	}
 
-	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-flash", "prompt", 0, false, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
 	if rec.Code != http.StatusBadRequest {
 		t.Fatalf("expected 400 for filtered empty upstream output, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -410,7 +410,7 @@ func TestHandleResponsesNonStreamReturns429WhenUpstreamHasOnlyThinking(t *testin
 		)),
 	}
 
-	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", true, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", 0, true, false, nil, nil, promptcompat.DefaultToolChoicePolicy(), "")
 	if rec.Code != http.StatusTooManyRequests {
 		t.Fatalf("expected 429 for thinking-only upstream output, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -432,7 +432,7 @@ func TestHandleResponsesNonStreamPromotesThinkingToolCallsWhenTextEmpty(t *testi
 		)),
 	}
 
-	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", true, false, []string{"read_file"}, nil, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_test", "deepseek-v4-pro", "prompt", 0, true, false, []string{"read_file"}, nil, promptcompat.DefaultToolChoicePolicy(), "")
 	if rec.Code != http.StatusOK {
 		t.Fatalf("expected 200 for thinking tool calls, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -462,7 +462,7 @@ func TestHandleResponsesNonStreamPromotesHiddenThinkingDSMLToolCallsWhenTextEmpt
 		Mode:    promptcompat.ToolChoiceRequired,
 		Allowed: map[string]struct{}{"read_file": {}},
 	}
-	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_hidden", "deepseek-v4-pro", "prompt", false, false, []string{"read_file"}, nil, policy, "")
+	h.handleResponsesNonStream(rec, resp, "owner-a", "resp_hidden", "deepseek-v4-pro", "prompt", 0, false, false, []string{"read_file"}, nil, policy, "")
 	if rec.Code != http.StatusOK {
 		t.Fatalf("expected 200 for hidden thinking tool calls, got %d body=%s", rec.Code, rec.Body.String())
 	}
@@ -509,7 +509,7 @@ func TestHandleResponsesStreamCoercesSchemaDeclaredStringArguments(t *testing.T)
 		Body:       io.NopCloser(strings.NewReader(streamBody)),
 	}
 
-	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_string_protect", "deepseek-v4-flash", "prompt", false, false, []string{"Write"}, toolsRaw, promptcompat.DefaultToolChoicePolicy(), "")
+	h.handleResponsesStream(rec, req, resp, "owner-a", "resp_string_protect", "deepseek-v4-flash", "prompt", 0, false, false, []string{"Write"}, toolsRaw, promptcompat.DefaultToolChoicePolicy(), "")
 
 	payload, ok := extractSSEEventPayload(rec.Body.String(), "response.function_call_arguments.done")
 	if !ok {

internal/httpapi/openai/shared/assistant_toolcalls.go

@@ -6,12 +6,12 @@ import (
 	"ds2api/internal/toolcall"
 )
 
-func DetectAssistantToolCalls(text, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult {
-	textParsed := toolcall.ParseStandaloneToolCallsDetailed(text, toolNames)
+func DetectAssistantToolCalls(rawText, visibleText, exposedThinking, detectionThinking string, toolNames []string) toolcall.ToolCallParseResult {
+	textParsed := toolcall.ParseStandaloneToolCallsDetailed(rawText, toolNames)
 	if len(textParsed.Calls) > 0 {
 		return textParsed
 	}
-	if strings.TrimSpace(text) != "" {
+	if strings.TrimSpace(visibleText) != "" {
 		return textParsed
 	}
 	thinking := detectionThinking

internal/httpapi/openai/shared/citation_links.go

@@ -7,25 +7,43 @@ import (
 	"strings"
 )
 
-var citationMarkerPattern = regexp.MustCompile(`(?i)\[citation:\s*(\d+)\]`)
+var citationMarkerPattern = regexp.MustCompile(`(?i)\[(citation|reference):\s*(\d+)\]`)
 
 func ReplaceCitationMarkersWithLinks(text string, links map[int]string) string {
 	if strings.TrimSpace(text) == "" || len(links) == 0 {
 		return text
 	}
+	zeroBasedReference := hasZeroBasedReferenceMarker(text)
 	return citationMarkerPattern.ReplaceAllStringFunc(text, func(match string) string {
 		sub := citationMarkerPattern.FindStringSubmatch(match)
-		if len(sub) < 2 {
+		if len(sub) < 3 {
 			return match
 		}
-		idx, err := strconv.Atoi(strings.TrimSpace(sub[1]))
-		if err != nil || idx <= 0 {
+		idx, err := strconv.Atoi(strings.TrimSpace(sub[2]))
+		if err != nil || idx < 0 {
 			return match
 		}
-		url := strings.TrimSpace(links[idx])
+		lookupIdx := idx
+		if strings.EqualFold(sub[1], "reference") && zeroBasedReference {
+			lookupIdx = idx + 1
+		}
+		url := strings.TrimSpace(links[lookupIdx])
 		if url == "" {
 			return match
 		}
 		return fmt.Sprintf("[%d](%s)", idx, url)
 	})
 }
+
+func hasZeroBasedReferenceMarker(text string) bool {
+	for _, sub := range citationMarkerPattern.FindAllStringSubmatch(text, -1) {
+		if len(sub) < 3 || !strings.EqualFold(sub[1], "reference") {
+			continue
+		}
+		idx, err := strconv.Atoi(strings.TrimSpace(sub[2]))
+		if err == nil && idx == 0 {
+			return true
+		}
+	}
+	return false
+}

internal/httpapi/openai/shared/leaked_output_sanitize.go

@@ -3,6 +3,8 @@ package shared
 import (
 	"regexp"
 	"strings"
+
+	"ds2api/internal/toolcall"
 )
 
 var emptyJSONFencePattern = regexp.MustCompile("(?is)```json\\s*```")
@@ -47,10 +49,42 @@ func sanitizeLeakedOutput(text string) string {
 	out = leakedThinkTagPattern.ReplaceAllString(out, "")
 	out = leakedBOSMarkerPattern.ReplaceAllString(out, "")
 	out = leakedMetaMarkerPattern.ReplaceAllString(out, "")
+	out = stripLeakedToolCallWrapperBlocks(out)
 	out = sanitizeLeakedAgentXMLBlocks(out)
 	return out
 }
 
+func stripLeakedToolCallWrapperBlocks(text string) string {
+	if text == "" {
+		return text
+	}
+	var b strings.Builder
+	pos := 0
+	for pos < len(text) {
+		tag, ok := toolcall.FindToolMarkupTagOutsideIgnored(text, pos)
+		if !ok {
+			b.WriteString(text[pos:])
+			break
+		}
+		if tag.Start > pos {
+			b.WriteString(text[pos:tag.Start])
+		}
+		if tag.Closing || tag.Name != "tool_calls" {
+			b.WriteString(text[tag.Start : tag.End+1])
+			pos = tag.End + 1
+			continue
+		}
+		closeTag, ok := toolcall.FindMatchingToolMarkupClose(text, tag)
+		if !ok {
+			b.WriteString(text[tag.Start : tag.End+1])
+			pos = tag.End + 1
+			continue
+		}
+		pos = closeTag.End + 1
+	}
+	return b.String()
+}
+
 func stripDanglingThinkSuffix(text string) string {
 	matches := leakedThinkTagPattern.FindAllStringIndex(text, -1)
 	if len(matches) == 0 {

internal/js/chat-stream/sse_parse_impl.js

@@ -308,6 +308,10 @@ function parseChunkForContent(chunk, thinkingEnabled, currentType, stripReferenc
   }
 
   if (val && typeof val === 'object') {
+    const directContent = asContentString(val, stripReferenceMarkers);
+    if (directContent) {
+      parts.push({ text: directContent, type: partType });
+    }
     const resp = val.response && typeof val.response === 'object' ? val.response : val;
     if (Array.isArray(resp.fragments)) {
       for (const frag of resp.fragments) {
@@ -593,6 +597,12 @@ function asContentString(v, stripReferenceMarkers = true) {
     if (Object.prototype.hasOwnProperty.call(v, 'v')) {
       return asContentString(v.v, stripReferenceMarkers);
     }
+    if (Object.prototype.hasOwnProperty.call(v, 'text')) {
+      return asContentString(v.text, stripReferenceMarkers);
+    }
+    if (Object.prototype.hasOwnProperty.call(v, 'value')) {
+      return asContentString(v.value, stripReferenceMarkers);
+    }
     return '';
   }
   if (v == null) {

internal/js/chat-stream/vercel_stream_impl.js

@@ -205,14 +205,14 @@ async function handleVercelStream(req, res, rawBody, payload) {
       if (detected.length > 0 && !toolCallsDoneEmitted) {
         toolCallsEmitted = true;
         toolCallsDoneEmitted = true;
-        sendDeltaFrame({ tool_calls: formatOpenAIStreamToolCalls(detected, streamToolCallIDs) });
+        sendDeltaFrame({ tool_calls: formatOpenAIStreamToolCalls(detected, streamToolCallIDs, payload.tools) });
       } else if (toolSieveEnabled) {
         const tailEvents = flushToolSieve(toolSieveState, toolNames);
         for (const evt of tailEvents) {
           if (evt.type === 'tool_calls' && Array.isArray(evt.calls) && evt.calls.length > 0) {
             toolCallsEmitted = true;
             toolCallsDoneEmitted = true;
-            sendDeltaFrame({ tool_calls: formatOpenAIStreamToolCalls(evt.calls, streamToolCallIDs) });
+            sendDeltaFrame({ tool_calls: formatOpenAIStreamToolCalls(evt.calls, streamToolCallIDs, payload.tools) });
             resetStreamToolCallState(streamToolCallIDs, streamToolNames);
             continue;
           }
@@ -352,14 +352,14 @@ async function handleVercelStream(req, res, rawBody, payload) {
                       const formatted = formatIncrementalToolCallDeltas(filtered, streamToolCallIDs);
                       if (formatted.length > 0) {
                         toolCallsEmitted = true;
-                        sendDeltaFrame({ tool_calls: formatted });
+                      sendDeltaFrame({ tool_calls: formatted });
                       }
                       continue;
                     }
                     if (evt.type === 'tool_calls') {
                       toolCallsEmitted = true;
                       toolCallsDoneEmitted = true;
-                      sendDeltaFrame({ tool_calls: formatOpenAIStreamToolCalls(evt.calls, streamToolCallIDs) });
+                      sendDeltaFrame({ tool_calls: formatOpenAIStreamToolCalls(evt.calls, streamToolCallIDs, payload.tools) });
                       resetStreamToolCallState(streamToolCallIDs, streamToolNames);
                       continue;
                     }
@@ -513,6 +513,11 @@ function observeContinueState(state, chunk) {
   if (chunk.p === 'response/status') {
     setContinueStatus(state, asString(chunk.v));
   }
+  if (chunk.p === 'response') {
+    observeContinueBatchPatches(state, 'response', chunk.v);
+  } else {
+    observeContinueBatchPatches(state, '', chunk.v);
+  }
   const response = chunk.v && typeof chunk.v === 'object' ? chunk.v.response : null;
   if (response && typeof response === 'object') {
     const id = numberValue(response.message_id);
@@ -534,13 +539,43 @@ function observeContinueState(state, chunk) {
   }
 }
 
+function observeContinueBatchPatches(state, parentPath, raw) {
+  if (!state || !Array.isArray(raw)) {
+    return;
+  }
+  for (const patch of raw) {
+    if (!patch || typeof patch !== 'object') {
+      continue;
+    }
+    const path = asString(patch.p).trim();
+    if (!path) {
+      continue;
+    }
+    let fullPath = path;
+    const parent = asString(parentPath).trim().replace(/^\/+|\/+$/g, '');
+    if (parent && !path.includes('/')) {
+      fullPath = `${parent}/${path}`;
+    }
+    switch (fullPath.replace(/^\/+|\/+$/g, '')) {
+      case 'response/status':
+      case 'status':
+      case 'response/quasi_status':
+      case 'quasi_status':
+        setContinueStatus(state, asString(patch.v));
+        break;
+      default:
+        break;
+    }
+  }
+}
+
 function setContinueStatus(state, status) {
   const normalized = asString(status).trim();
   if (!normalized) {
     return;
   }
   state.lastStatus = normalized;
-  if (normalized.toUpperCase() === 'FINISHED') {
+  if (['FINISHED', 'CONTENT_FILTER'].includes(normalized.toUpperCase())) {
     state.finished = true;
   }
 }
@@ -549,7 +584,7 @@ function shouldAutoContinue(state) {
   if (!state || state.finished || !state.sessionID || state.responseMessageID <= 0) {
     return false;
   }
-  return ['WIP', 'INCOMPLETE', 'AUTO_CONTINUE'].includes(asString(state.lastStatus).trim().toUpperCase());
+  return ['INCOMPLETE', 'AUTO_CONTINUE'].includes(asString(state.lastStatus).trim().toUpperCase());
 }
 
 function numberValue(v) {

internal/js/helpers/stream-tool-sieve/format.js

@@ -2,11 +2,12 @@
 
 const crypto = require('crypto');
 
-function formatOpenAIStreamToolCalls(calls, idStore) {
+function formatOpenAIStreamToolCalls(calls, idStore, toolsRaw) {
   if (!Array.isArray(calls) || calls.length === 0) {
     return [];
   }
-  return calls.map((c, idx) => ({
+  const normalized = normalizeParsedToolCallsForSchemas(calls, toolsRaw);
+  return normalized.map((c, idx) => ({
     index: idx,
     id: ensureStreamToolCallID(idStore, idx),
     type: 'function',
@@ -17,6 +18,194 @@ function formatOpenAIStreamToolCalls(calls, idStore) {
   }));
 }
 
+function normalizeParsedToolCallsForSchemas(calls, toolsRaw) {
+  if (!Array.isArray(calls) || calls.length === 0) {
+    return calls;
+  }
+  const schemas = buildToolSchemaIndex(toolsRaw);
+  if (!schemas) {
+    return calls;
+  }
+  let changedAny = false;
+  const out = calls.map((call) => {
+    const name = String(call && call.name || '').trim().toLowerCase();
+    const schema = schemas[name];
+    if (!schema || !call || !call.input || typeof call.input !== 'object' || Array.isArray(call.input)) {
+      return call;
+    }
+    const [normalized, changed] = normalizeToolValueWithSchema(call.input, schema);
+    if (!changed || !normalized || typeof normalized !== 'object' || Array.isArray(normalized)) {
+      return call;
+    }
+    changedAny = true;
+    return { ...call, input: normalized };
+  });
+  return changedAny ? out : calls;
+}
+
+function buildToolSchemaIndex(toolsRaw) {
+  if (!Array.isArray(toolsRaw) || toolsRaw.length === 0) {
+    return null;
+  }
+  const out = {};
+  for (const item of toolsRaw) {
+    if (!item || typeof item !== 'object' || Array.isArray(item)) {
+      continue;
+    }
+    const [name, schema] = extractToolNameAndSchema(item);
+    if (!name || !schema || typeof schema !== 'object' || Array.isArray(schema)) {
+      continue;
+    }
+    out[name.toLowerCase()] = schema;
+  }
+  return Object.keys(out).length > 0 ? out : null;
+}
+
+function extractToolNameAndSchema(tool) {
+  const fn = tool && typeof tool.function === 'object' && !Array.isArray(tool.function) ? tool.function : null;
+  const name = firstNonEmptyString(tool.name, fn && fn.name);
+  const schema = firstNonNil(
+    tool.parameters,
+    tool.input_schema,
+    tool.inputSchema,
+    tool.schema,
+    fn && fn.parameters,
+    fn && fn.input_schema,
+    fn && fn.inputSchema,
+    fn && fn.schema,
+  );
+  return [name, schema];
+}
+
+function normalizeToolValueWithSchema(value, schema) {
+  if (value == null || !schema || typeof schema !== 'object' || Array.isArray(schema)) {
+    return [value, false];
+  }
+  if (shouldCoerceSchemaToString(schema)) {
+    return stringifySchemaValue(value);
+  }
+  if (looksLikeObjectSchema(schema)) {
+    if (!value || typeof value !== 'object' || Array.isArray(value)) {
+      return [value, false];
+    }
+    const properties = schema.properties && typeof schema.properties === 'object' && !Array.isArray(schema.properties) ? schema.properties : null;
+    const additional = schema.additionalProperties;
+    let changed = false;
+    const out = {};
+    for (const [key, current] of Object.entries(value)) {
+      let next = current;
+      let fieldChanged = false;
+      if (properties && Object.prototype.hasOwnProperty.call(properties, key)) {
+        [next, fieldChanged] = normalizeToolValueWithSchema(current, properties[key]);
+      } else if (additional != null) {
+        [next, fieldChanged] = normalizeToolValueWithSchema(current, additional);
+      }
+      out[key] = next;
+      changed = changed || fieldChanged;
+    }
+    return changed ? [out, true] : [value, false];
+  }
+  if (looksLikeArraySchema(schema)) {
+    if (!Array.isArray(value) || value.length === 0 || schema.items == null) {
+      return [value, false];
+    }
+    let changed = false;
+    const out = value.map((item, idx) => {
+      const itemSchema = Array.isArray(schema.items) ? schema.items[idx] : schema.items;
+      if (itemSchema == null) {
+        return item;
+      }
+      const [next, itemChanged] = normalizeToolValueWithSchema(item, itemSchema);
+      changed = changed || itemChanged;
+      return next;
+    });
+    return changed ? [out, true] : [value, false];
+  }
+  return [value, false];
+}
+
+function shouldCoerceSchemaToString(schema) {
+  if (!schema || typeof schema !== 'object' || Array.isArray(schema)) {
+    return false;
+  }
+  if (typeof schema.const === 'string') {
+    return true;
+  }
+  if (Array.isArray(schema.enum) && schema.enum.length > 0 && schema.enum.every((item) => typeof item === 'string')) {
+    return true;
+  }
+  if (typeof schema.type === 'string') {
+    return schema.type.trim().toLowerCase() === 'string';
+  }
+  if (Array.isArray(schema.type) && schema.type.length > 0) {
+    let hasString = false;
+    for (const item of schema.type) {
+      if (typeof item !== 'string') {
+        return false;
+      }
+      const typ = item.trim().toLowerCase();
+      if (typ === 'string') {
+        hasString = true;
+      } else if (typ !== 'null') {
+        return false;
+      }
+    }
+    return hasString;
+  }
+  return false;
+}
+
+function looksLikeObjectSchema(schema) {
+  return !!schema && typeof schema === 'object' && !Array.isArray(schema) && (
+    (typeof schema.type === 'string' && schema.type.trim().toLowerCase() === 'object') ||
+    (schema.properties && typeof schema.properties === 'object' && !Array.isArray(schema.properties)) ||
+    schema.additionalProperties != null
+  );
+}
+
+function looksLikeArraySchema(schema) {
+  return !!schema && typeof schema === 'object' && !Array.isArray(schema) && (
+    (typeof schema.type === 'string' && schema.type.trim().toLowerCase() === 'array') ||
+    schema.items != null
+  );
+}
+
+function stringifySchemaValue(value) {
+  if (value == null) {
+    return [value, false];
+  }
+  if (typeof value === 'string') {
+    return [value, false];
+  }
+  try {
+    return [JSON.stringify(value), true];
+  } catch {
+    return [value, false];
+  }
+}
+
+function firstNonNil(...values) {
+  for (const value of values) {
+    if (value != null) {
+      return value;
+    }
+  }
+  return null;
+}
+
+function firstNonEmptyString(...values) {
+  for (const value of values) {
+    if (typeof value !== 'string') {
+      continue;
+    }
+    const trimmed = value.trim();
+    if (trimmed) {
+      return trimmed;
+    }
+  }
+  return '';
+}
+
 function ensureStreamToolCallID(idStore, index) {
   if (!(idStore instanceof Map)) {
     return `call_${newCallID()}`;

internal/promptcompat/history_transcript.go

@@ -1,13 +1,12 @@
 package promptcompat
 
 import (
-	"fmt"
 	"strings"
 
 	"ds2api/internal/prompt"
 )
 
-const historySplitInjectedFilename = "IGNORE"
+const CurrentInputContextFilename = "history.txt"
 
 func BuildOpenAIHistoryTranscript(messages []any) string {
 	return buildOpenAIInjectedFileTranscript(messages)
@@ -32,5 +31,5 @@ func buildOpenAIInjectedFileTranscript(messages []any) string {
 	if transcript == "" {
 		return ""
 	}
-	return fmt.Sprintf("[file content end]\n\n%s\n\n[file name]: %s\n[file content begin]\n", transcript, historySplitInjectedFilename)
+	return transcript
 }

internal/promptcompat/request_normalize.go

@@ -39,20 +39,22 @@ func NormalizeOpenAIChatRequest(store ConfigReader, req map[string]any, traceID
 	refFileIDs := CollectOpenAIRefFileIDs(req)
 
 	return StandardRequest{
-		Surface:        "openai_chat",
-		RequestedModel: strings.TrimSpace(model),
-		ResolvedModel:  resolvedModel,
-		ResponseModel:  responseModel,
-		Messages:       messagesRaw,
-		ToolsRaw:       req["tools"],
-		FinalPrompt:    finalPrompt,
-		ToolNames:      toolNames,
-		ToolChoice:     toolPolicy,
-		Stream:         util.ToBool(req["stream"]),
-		Thinking:       thinkingEnabled,
-		Search:         searchEnabled,
-		RefFileIDs:     refFileIDs,
-		PassThrough:    passThrough,
+		Surface:         "openai_chat",
+		RequestedModel:  strings.TrimSpace(model),
+		ResolvedModel:   resolvedModel,
+		ResponseModel:   responseModel,
+		Messages:        messagesRaw,
+		PromptTokenText: finalPrompt,
+		ToolsRaw:        req["tools"],
+		FinalPrompt:     finalPrompt,
+		ToolNames:       toolNames,
+		ToolChoice:      toolPolicy,
+		Stream:          util.ToBool(req["stream"]),
+		Thinking:        thinkingEnabled,
+		Search:          searchEnabled,
+		RefFileIDs:      refFileIDs,
+		RefFileTokens:   estimateInlineFileTokens(req),
+		PassThrough:     passThrough,
 	}, nil
 }
 
@@ -99,20 +101,22 @@ func NormalizeOpenAIResponsesRequest(store ConfigReader, req map[string]any, tra
 	refFileIDs := CollectOpenAIRefFileIDs(req)
 
 	return StandardRequest{
-		Surface:        "openai_responses",
-		RequestedModel: model,
-		ResolvedModel:  resolvedModel,
-		ResponseModel:  model,
-		Messages:       messagesRaw,
-		ToolsRaw:       req["tools"],
-		FinalPrompt:    finalPrompt,
-		ToolNames:      toolNames,
-		ToolChoice:     toolPolicy,
-		Stream:         util.ToBool(req["stream"]),
-		Thinking:       thinkingEnabled,
-		Search:         searchEnabled,
-		RefFileIDs:     refFileIDs,
-		PassThrough:    passThrough,
+		Surface:         "openai_responses",
+		RequestedModel:  model,
+		ResolvedModel:   resolvedModel,
+		ResponseModel:   model,
+		Messages:        messagesRaw,
+		PromptTokenText: finalPrompt,
+		ToolsRaw:        req["tools"],
+		FinalPrompt:     finalPrompt,
+		ToolNames:       toolNames,
+		ToolChoice:      toolPolicy,
+		Stream:          util.ToBool(req["stream"]),
+		Thinking:        thinkingEnabled,
+		Search:          searchEnabled,
+		RefFileIDs:      refFileIDs,
+		RefFileTokens:   estimateInlineFileTokens(req),
+		PassThrough:     passThrough,
 	}, nil
 }
 
@@ -356,3 +360,30 @@ func namesToSet(names []string) map[string]struct{} {
 	}
 	return out
 }
+
+// estimateInlineFileTokens extracts the byte count stashed by PreprocessInlineFileInputs
+// and converts it to a conservative token estimate. Inline files are typically images or
+// documents that the upstream model will process; we use bytes/3 (rather than bytes/4)
+// as a slightly pessimistic approximation so the returned context token count stays
+// safely above the real value.
+func estimateInlineFileTokens(req map[string]any) int {
+	raw, ok := req["_inline_file_bytes"]
+	if !ok {
+		return 0
+	}
+	var bytes int
+	switch v := raw.(type) {
+	case int:
+		bytes = v
+	case int64:
+		bytes = int(v)
+	case float64:
+		bytes = int(v)
+	default:
+		return 0
+	}
+	if bytes <= 0 {
+		return 0
+	}
+	return bytes / 3
+}

internal/promptcompat/standard_request.go

@@ -9,6 +9,7 @@ type StandardRequest struct {
 	ResponseModel           string
 	Messages                []any
 	HistoryText             string
+	PromptTokenText         string
 	CurrentInputFileApplied bool
 	ToolsRaw                any
 	FinalPrompt             string
@@ -18,6 +19,7 @@ type StandardRequest struct {
 	Thinking                bool
 	Search                  bool
 	RefFileIDs              []string
+	RefFileTokens           int
 	PassThrough             map[string]any
 }
 

internal/promptcompat/standard_request_test.go

@@ -13,7 +13,7 @@ func TestStandardRequestCompletionPayloadSetsModelTypeFromResolvedModel(t *testi
 		{name: "default", model: "deepseek-v4-flash", thinking: false, search: false, modelType: "default"},
 		{name: "default_nothinking", model: "deepseek-v4-flash-nothinking", thinking: false, search: false, modelType: "default"},
 		{name: "expert", model: "deepseek-v4-pro", thinking: true, search: false, modelType: "expert"},
-		{name: "vision", model: "deepseek-v4-vision-search", thinking: false, search: true, modelType: "vision"},
+		{name: "vision", model: "deepseek-v4-vision", thinking: true, search: false, modelType: "vision"},
 	}
 
 	for _, tc := range tests {

internal/promptcompat/tool_prompt.go

@@ -30,13 +30,7 @@ func injectToolPrompt(messages []map[string]any, tools []any, policy ToolChoiceP
 		if !ok {
 			continue
 		}
-		fn, _ := tool["function"].(map[string]any)
-		if len(fn) == 0 {
-			fn = tool
-		}
-		name, _ := fn["name"].(string)
-		desc, _ := fn["description"].(string)
-		schema, _ := fn["parameters"].(map[string]any)
+		name, desc, schema := toolcall.ExtractToolMeta(tool)
 		name = strings.TrimSpace(name)
 		if !isAllowed(name) {
 			continue

internal/server/router.go

@@ -98,6 +98,14 @@ func NewApp() (*App, error) {
 	r.Get("/v1/responses/{response_id}", responsesHandler.GetResponseByID)
 	r.Post("/v1/files", filesHandler.UploadFile)
 	r.Post("/v1/embeddings", embeddingsHandler.Embeddings)
+	// Root OpenAI aliases support clients configured with the bare DS2API service URL.
+	r.Get("/models", modelsHandler.ListModels)
+	r.Get("/models/{model_id}", modelsHandler.GetModel)
+	r.Post("/chat/completions", chatHandler.ChatCompletions)
+	r.Post("/responses", responsesHandler.Responses)
+	r.Get("/responses/{response_id}", responsesHandler.GetResponseByID)
+	r.Post("/files", filesHandler.UploadFile)
+	r.Post("/embeddings", embeddingsHandler.Embeddings)
 	claude.RegisterRoutes(r, claudeHandler)
 	gemini.RegisterRoutes(r, geminiHandler)
 	r.Route("/admin", func(ar chi.Router) {

internal/server/router_routes_test.go

@@ -37,6 +37,13 @@ func TestAPIRoutesRemainRegistered(t *testing.T) {
 		"GET /v1/responses/{response_id}",
 		"POST /v1/files",
 		"POST /v1/embeddings",
+		"GET /models",
+		"GET /models/{model_id}",
+		"POST /chat/completions",
+		"POST /responses",
+		"GET /responses/{response_id}",
+		"POST /files",
+		"POST /embeddings",
 		"GET /anthropic/v1/models",
 		"POST /anthropic/v1/messages",
 		"POST /anthropic/v1/messages/count_tokens",

internal/sse/parser.go

@@ -244,11 +244,29 @@ func appendChunkValueContent(v any, partType string, newType *string, parts *[]C
 		}
 		*parts = append(*parts, pp...)
 	case map[string]any:
+		if appendObjectContentByPath(path, val, partType, parts) {
+			return false
+		}
 		appendWrappedFragments(val, partType, newType, parts)
 	}
 	return false
 }
 
+func appendObjectContentByPath(path string, val map[string]any, partType string, parts *[]ContentPart) bool {
+	if path != "response/content" && path != "response/thinking_content" && path != "" {
+		return false
+	}
+	text, _ := val["text"].(string)
+	if text == "" {
+		text, _ = val["content"].(string)
+	}
+	if text == "" {
+		return false
+	}
+	appendContentPart(parts, text, partType)
+	return true
+}
+
 func appendWrappedFragments(val map[string]any, partType string, newType *string, parts *[]ContentPart) {
 	resp := val
 	if wrapped, ok := val["response"].(map[string]any); ok {

internal/sse/parser_test.go

@@ -163,3 +163,44 @@ func TestParseSSEChunkForContentStripsLeakedThinkTagsFromText(t *testing.T) {
 		t.Fatalf("expected leaked think tag to be stripped, got %#v", parts[0])
 	}
 }
+
+func TestParseSSEChunkForContentResponseContentObjectShape(t *testing.T) {
+	chunk := map[string]any{
+		"p": "response/content",
+		"v": map[string]any{"text": "对象内容"},
+	}
+	parts, finished, _ := ParseSSEChunkForContent(chunk, false, "text")
+	if finished {
+		t.Fatal("expected unfinished")
+	}
+	if len(parts) != 1 || parts[0].Text != "对象内容" || parts[0].Type != "text" {
+		t.Fatalf("unexpected parts: %#v", parts)
+	}
+}
+
+func TestParseSSEChunkForThinkingContentObjectShape(t *testing.T) {
+	chunk := map[string]any{
+		"p": "response/thinking_content",
+		"v": map[string]any{"content": "对象思考"},
+	}
+	parts, finished, _ := ParseSSEChunkForContent(chunk, true, "thinking")
+	if finished {
+		t.Fatal("expected unfinished")
+	}
+	if len(parts) != 1 || parts[0].Text != "对象思考" || parts[0].Type != "thinking" {
+		t.Fatalf("unexpected parts: %#v", parts)
+	}
+}
+
+func TestParseSSEChunkForContentObjectShapeWithoutPath(t *testing.T) {
+	chunk := map[string]any{
+		"v": map[string]any{"text": "无路径对象内容"},
+	}
+	parts, finished, _ := ParseSSEChunkForContent(chunk, false, "text")
+	if finished {
+		t.Fatal("expected unfinished")
+	}
+	if len(parts) != 1 || parts[0].Text != "无路径对象内容" || parts[0].Type != "text" {
+		t.Fatalf("unexpected parts: %#v", parts)
+	}
+}

internal/sse/stream.go

@@ -4,12 +4,15 @@ import (
 	"bufio"
 	"context"
 	"io"
+	"time"
 )
 
 const (
 	parsedLineBufferSize = 128
 	scannerBufferSize    = 64 * 1024
 	maxScannerLineSize   = 2 * 1024 * 1024
+	minFlushChars        = 160
+	maxFlushWait         = 80 * time.Millisecond
 )
 
 // StartParsedLinePump scans an upstream DeepSeek SSE body and emits normalized
@@ -20,21 +23,123 @@ func StartParsedLinePump(ctx context.Context, body io.Reader, thinkingEnabled bo
 	done := make(chan error, 1)
 	go func() {
 		defer close(out)
-		scanner := bufio.NewScanner(body)
-		scanner.Buffer(make([]byte, 0, scannerBufferSize), maxScannerLineSize)
+		type scanItem struct {
+			line []byte
+			err  error
+			eof  bool
+		}
+		lineCh := make(chan scanItem, 1)
+		stopScanner := make(chan struct{})
+		defer close(stopScanner)
+		go func() {
+			sendScanItem := func(item scanItem) bool {
+				select {
+				case lineCh <- item:
+					return true
+				case <-ctx.Done():
+					return false
+				case <-stopScanner:
+					return false
+				}
+			}
+			defer close(lineCh)
+			scanner := bufio.NewScanner(body)
+			scanner.Buffer(make([]byte, 0, scannerBufferSize), maxScannerLineSize)
+			for scanner.Scan() {
+				line := append([]byte{}, scanner.Bytes()...)
+				if !sendScanItem(scanItem{line: line}) {
+					return
+				}
+			}
+			_ = sendScanItem(scanItem{err: scanner.Err(), eof: true})
+		}()
+
+		ticker := time.NewTicker(maxFlushWait)
+		defer ticker.Stop()
 		currentType := initialType
-		for scanner.Scan() {
-			line := append([]byte{}, scanner.Bytes()...)
-			result := ParseDeepSeekContentLine(line, thinkingEnabled, currentType)
-			currentType = result.NextType
+		var pending *LineResult
+		pendingChars := 0
+
+		sendResult := func(r LineResult) bool {
+			select {
+			case out <- r:
+				return true
+			case <-ctx.Done():
+				done <- ctx.Err()
+				return false
+			}
+		}
+
+		flushPending := func() bool {
+			if pending == nil {
+				return true
+			}
+			if !sendResult(*pending) {
+				return false
+			}
+			pending = nil
+			pendingChars = 0
+			return true
+		}
+
+		for {
 			select {
-			case out <- result:
 			case <-ctx.Done():
 				done <- ctx.Err()
 				return
+			case <-ticker.C:
+				if !flushPending() {
+					return
+				}
+			case item, ok := <-lineCh:
+				if !ok || item.eof {
+					if !flushPending() {
+						return
+					}
+					done <- item.err
+					return
+				}
+				line := item.line
+				result := ParseDeepSeekContentLine(line, thinkingEnabled, currentType)
+				currentType = result.NextType
+
+				canAccumulate := result.Parsed && !result.Stop && result.ErrorMessage == "" && !result.ContentFilter && result.ResponseMessageID == 0
+				if canAccumulate {
+					lineChars := 0
+					for _, p := range result.Parts {
+						lineChars += len(p.Text)
+					}
+					for _, p := range result.ToolDetectionThinkingParts {
+						lineChars += len(p.Text)
+					}
+					if lineChars > 0 {
+						if pending == nil {
+							cp := result
+							pending = &cp
+						} else {
+							pending.Parts = append(pending.Parts, result.Parts...)
+							pending.ToolDetectionThinkingParts = append(pending.ToolDetectionThinkingParts, result.ToolDetectionThinkingParts...)
+							pending.NextType = result.NextType
+						}
+						pendingChars += lineChars
+						if pendingChars < minFlushChars {
+							continue
+						}
+						if !flushPending() {
+							return
+						}
+						continue
+					}
+				}
+
+				if !flushPending() {
+					return
+				}
+				if !sendResult(result) {
+					return
+				}
 			}
 		}
-		done <- scanner.Err()
 	}()
 	return out, done
 }

internal/sse/stream_edge_test.go

@@ -38,8 +38,8 @@ func TestStartParsedLinePumpMultipleLines(t *testing.T) {
 	if err := <-done; err != nil {
 		t.Fatalf("unexpected error: %v", err)
 	}
-	if len(collected) < 3 {
-		t.Fatalf("expected at least 3 results, got %d", len(collected))
+	if len(collected) < 2 {
+		t.Fatalf("expected at least 2 results, got %d", len(collected))
 	}
 	// First should be thinking
 	if collected[0].Parts[0].Type != "thinking" {
@@ -175,3 +175,31 @@ func TestStartParsedLinePumpThinkingDisabled(t *testing.T) {
 		t.Fatalf("expected at least 1 part, got %d", len(parts))
 	}
 }
+
+func TestStartParsedLinePumpAccumulatesSmallChunks(t *testing.T) {
+	body := strings.NewReader(
+		"data: {\"p\":\"response/content\",\"v\":\"h\"}\n" +
+			"data: {\"p\":\"response/content\",\"v\":\"i\"}\n" +
+			"data: [DONE]\n",
+	)
+
+	results, done := StartParsedLinePump(context.Background(), body, false, "text")
+
+	collected := make([]LineResult, 0)
+	for r := range results {
+		collected = append(collected, r)
+	}
+	if err := <-done; err != nil {
+		t.Fatalf("unexpected error: %v", err)
+	}
+
+	if len(collected) != 2 {
+		t.Fatalf("expected 2 results (accumulated content + done), got %d", len(collected))
+	}
+	if len(collected[0].Parts) != 2 {
+		t.Fatalf("expected 2 accumulated parts, got %d", len(collected[0].Parts))
+	}
+	if !collected[1].Stop {
+		t.Fatal("expected second result to stop")
+	}
+}

internal/toolcall/toolcalls_parse.go

@@ -92,11 +92,45 @@ func filterToolCallsDetailed(parsed []ParsedToolCall) ([]ParsedToolCall, []strin
 		if tc.Input == nil {
 			tc.Input = map[string]any{}
 		}
+		if len(tc.Input) > 0 && !toolCallInputHasMeaningfulValue(tc.Input) {
+			continue
+		}
 		out = append(out, tc)
 	}
 	return out, nil
 }
 
+func toolCallInputHasMeaningfulValue(v any) bool {
+	switch x := v.(type) {
+	case nil:
+		return false
+	case string:
+		return strings.TrimSpace(x) != ""
+	case map[string]any:
+		if len(x) == 0 {
+			return false
+		}
+		for _, child := range x {
+			if toolCallInputHasMeaningfulValue(child) {
+				return true
+			}
+		}
+		return false
+	case []any:
+		if len(x) == 0 {
+			return false
+		}
+		for _, child := range x {
+			if toolCallInputHasMeaningfulValue(child) {
+				return true
+			}
+		}
+		return false
+	default:
+		return true
+	}
+}
+
 func looksLikeToolCallSyntax(text string) bool {
 	hasDSML, hasCanonical := ContainsToolCallWrapperSyntaxOutsideIgnored(text)
 	return hasDSML || hasCanonical

internal/toolcall/toolcalls_schema_normalize.go

@@ -48,7 +48,7 @@ func buildToolSchemaIndex(toolsRaw any) map[string]any {
 		if !ok {
 			continue
 		}
-		name, schema := extractToolNameAndSchema(tool)
+		name, _, schema := ExtractToolMeta(tool)
 		if name == "" || schema == nil {
 			continue
 		}
@@ -60,24 +60,31 @@ func buildToolSchemaIndex(toolsRaw any) map[string]any {
 	return out
 }
 
-func extractToolNameAndSchema(tool map[string]any) (string, any) {
+func ExtractToolMeta(tool map[string]any) (string, string, any) {
 	name := strings.TrimSpace(asStringValue(tool["name"]))
-	schema := tool["parameters"]
-	if schema == nil {
-		schema = tool["input_schema"]
-	}
+	desc := strings.TrimSpace(asStringValue(tool["description"]))
+	schema := firstNonNil(
+		tool["parameters"],
+		tool["input_schema"],
+		tool["inputSchema"],
+		tool["schema"],
+	)
 	if fn, ok := tool["function"].(map[string]any); ok {
 		if name == "" {
 			name = strings.TrimSpace(asStringValue(fn["name"]))
 		}
-		if schema == nil {
-			schema = fn["parameters"]
-		}
-		if schema == nil {
-			schema = fn["input_schema"]
+		if desc == "" {
+			desc = strings.TrimSpace(asStringValue(fn["description"]))
 		}
+		schema = firstNonNil(
+			schema,
+			fn["parameters"],
+			fn["input_schema"],
+			fn["inputSchema"],
+			fn["schema"],
+		)
 	}
-	return name, schema
+	return name, desc, schema
 }
 
 func normalizeToolValueWithSchema(value any, schema any) (any, bool) {
@@ -264,3 +271,12 @@ func asStringValue(v any) string {
 	}
 	return ""
 }
+
+func firstNonNil(values ...any) any {
+	for _, value := range values {
+		if value != nil {
+			return value
+		}
+	}
+	return nil
+}

internal/toolcall/toolcalls_schema_normalize_test.go

@@ -110,3 +110,52 @@ func TestNormalizeParsedToolCallsForSchemasLeavesAmbiguousUnionUnchanged(t *test
 		t.Fatalf("expected ambiguous union to stay unchanged, got %#v", got[0].Input["taskId"])
 	}
 }
+
+func TestNormalizeParsedToolCallsForSchemasSupportsCamelCaseInputSchema(t *testing.T) {
+	toolsRaw := []any{
+		map[string]any{
+			"name": "Write",
+			"inputSchema": map[string]any{
+				"type": "object",
+				"properties": map[string]any{
+					"content": map[string]any{"type": "string"},
+				},
+			},
+		},
+	}
+	calls := []ParsedToolCall{{Name: "Write", Input: map[string]any{"content": map[string]any{"message": "hi"}}}}
+	got := NormalizeParsedToolCallsForSchemas(calls, toolsRaw)
+	if got[0].Input["content"] != `{"message":"hi"}` {
+		t.Fatalf("expected camelCase inputSchema content coercion, got %#v", got[0].Input["content"])
+	}
+}
+
+func TestNormalizeParsedToolCallsForSchemasPreservesArrayWhenSchemaSaysArray(t *testing.T) {
+	toolsRaw := []any{
+		map[string]any{
+			"name": "todowrite",
+			"inputSchema": map[string]any{
+				"type": "object",
+				"properties": map[string]any{
+					"todos": map[string]any{
+						"type": "array",
+						"items": map[string]any{
+							"type": "object",
+							"properties": map[string]any{
+								"content":  map[string]any{"type": "string"},
+								"status":   map[string]any{"type": "string"},
+								"priority": map[string]any{"type": "string"},
+							},
+						},
+					},
+				},
+			},
+		},
+	}
+	todos := []any{map[string]any{"content": "x", "status": "pending", "priority": "high"}}
+	calls := []ParsedToolCall{{Name: "todowrite", Input: map[string]any{"todos": todos}}}
+	got := NormalizeParsedToolCallsForSchemas(calls, toolsRaw)
+	if !reflect.DeepEqual(got[0].Input["todos"], todos) {
+		t.Fatalf("expected todos array preserved, got %#v want %#v", got[0].Input["todos"], todos)
+	}
+}

internal/toolcall/toolcalls_test.go

@@ -323,6 +323,28 @@ func TestParseToolCallsDetailedMarksToolCallsSyntax(t *testing.T) {
 	}
 }
 
+func TestParseToolCallsRejectsAllEmptyParameterPayload(t *testing.T) {
+	text := `<tool_calls><invoke name="Bash"><parameter name="command"></parameter><parameter name="description">   </parameter><parameter name="timeout"></parameter></invoke></tool_calls>`
+	res := ParseToolCallsDetailed(text, []string{"Bash"})
+	if !res.SawToolCallSyntax {
+		t.Fatalf("expected tool syntax to be detected, got %#v", res)
+	}
+	if len(res.Calls) != 0 {
+		t.Fatalf("expected all-empty payload to be rejected, got %#v", res.Calls)
+	}
+}
+
+func TestParseToolCallsPreservesExplicitZeroArgToolCall(t *testing.T) {
+	text := `<tool_calls><invoke name="noop"></invoke></tool_calls>`
+	res := ParseToolCallsDetailed(text, []string{"noop"})
+	if len(res.Calls) != 1 {
+		t.Fatalf("expected zero-arg tool call to remain valid, got %#v", res.Calls)
+	}
+	if len(res.Calls[0].Input) != 0 {
+		t.Fatalf("expected empty input map for zero-arg tool call, got %#v", res.Calls[0].Input)
+	}
+}
+
 func TestParseToolCallsSupportsInlineJSONToolObject(t *testing.T) {
 	text := `<tool_calls><invoke name="Bash">{"input":{"command":"pwd","description":"show cwd"}}</invoke></tool_calls>`
 	calls := ParseToolCalls(text, []string{"bash"})

internal/toolstream/tool_sieve_xml.go

@@ -44,14 +44,21 @@ func consumeXMLToolCapture(captured string, toolNames []string) (prefix string,
 		xmlBlock := captured[tag.Start : closeTag.End+1]
 		prefixPart := captured[:tag.Start]
 		suffixPart := captured[closeTag.End+1:]
-		parsed := toolcall.ParseToolCalls(xmlBlock, toolNames)
-		if len(parsed) > 0 {
+		parsed := toolcall.ParseStandaloneToolCallsDetailed(xmlBlock, toolNames)
+		if len(parsed.Calls) > 0 {
 			prefixPart, suffixPart = trimWrappingJSONFence(prefixPart, suffixPart)
 			if best == nil || tag.Start < best.start {
-				best = &candidate{start: tag.Start, prefix: prefixPart, calls: parsed, suffix: suffixPart}
+				best = &candidate{start: tag.Start, prefix: prefixPart, calls: parsed.Calls, suffix: suffixPart}
 			}
 			break
 		}
+		if parsed.SawToolCallSyntax {
+			if rejected == nil || tag.Start < rejected.start {
+				rejected = &rejectedBlock{start: tag.Start, prefix: prefixPart, suffix: suffixPart}
+			}
+			searchFrom = tag.End + 1
+			continue
+		}
 		if rejected == nil || tag.Start < rejected.start {
 			rejected = &rejectedBlock{start: tag.Start, prefix: prefixPart + xmlBlock, suffix: suffixPart}
 		}
@@ -75,10 +82,13 @@ func consumeXMLToolCapture(captured string, toolNames []string) (prefix string,
 				xmlBlock := "<tool_calls>" + captured[invokeTag.Start:closeTag.End+1]
 				prefixPart := captured[:invokeTag.Start]
 				suffixPart := captured[closeTag.End+1:]
-				parsed := toolcall.ParseToolCalls(xmlBlock, toolNames)
-				if len(parsed) > 0 {
+				parsed := toolcall.ParseStandaloneToolCallsDetailed(xmlBlock, toolNames)
+				if len(parsed.Calls) > 0 {
 					prefixPart, suffixPart = trimWrappingJSONFence(prefixPart, suffixPart)
-					return prefixPart, parsed, suffixPart, true
+					return prefixPart, parsed.Calls, suffixPart, true
+				}
+				if parsed.SawToolCallSyntax {
+					return prefixPart, nil, suffixPart, true
 				}
 				return prefixPart + captured[invokeTag.Start:closeTag.End+1], nil, suffixPart, true
 			}

internal/toolstream/tool_sieve_xml_test.go

@@ -288,7 +288,7 @@ func TestProcessToolSieveNonToolXMLKeepsSuffixForToolParsing(t *testing.T) {
 	}
 }
 
-func TestProcessToolSievePassesThroughMalformedExecutableXMLBlock(t *testing.T) {
+func TestProcessToolSieveSuppressesMalformedExecutableXMLBlock(t *testing.T) {
 	var state State
 	chunk := `<tool_calls><invoke name="read_file"><param>{"path":"README.md"}</param></invoke></tool_calls>`
 	events := ProcessChunk(&state, chunk, []string{"read_file"})
@@ -302,10 +302,39 @@ func TestProcessToolSievePassesThroughMalformedExecutableXMLBlock(t *testing.T)
 	}
 
 	if toolCalls != 0 {
-		t.Fatalf("expected malformed executable-looking XML to stay text, got %d events=%#v", toolCalls, events)
+		t.Fatalf("expected malformed executable-looking XML not to become a tool call, got %d events=%#v", toolCalls, events)
 	}
-	if textContent.String() != chunk {
-		t.Fatalf("expected malformed executable-looking XML to pass through unchanged, got %q", textContent.String())
+	if textContent.Len() != 0 {
+		t.Fatalf("expected malformed executable-looking XML to be suppressed, got %q", textContent.String())
+	}
+}
+
+func TestProcessToolSieveSuppressesAllEmptyDSMLToolBlock(t *testing.T) {
+	var state State
+	chunk := strings.Join([]string{
+		`<|DSML|tool_calls>`,
+		`<|DSML|invoke name="Bash">`,
+		`<|DSML|parameter name="command"></|DSML|parameter>`,
+		`<|DSML|parameter name="description">   </|DSML|parameter>`,
+		`<|DSML|parameter name="timeout"></|DSML|parameter>`,
+		`</|DSML|invoke>`,
+		`</|DSML|tool_calls>`,
+	}, "\n")
+	events := ProcessChunk(&state, chunk, []string{"Bash"})
+	events = append(events, Flush(&state, []string{"Bash"})...)
+
+	var textContent strings.Builder
+	toolCalls := 0
+	for _, evt := range events {
+		textContent.WriteString(evt.Content)
+		toolCalls += len(evt.ToolCalls)
+	}
+
+	if toolCalls != 0 {
+		t.Fatalf("expected all-empty DSML block not to produce tool calls, got %d events=%#v", toolCalls, events)
+	}
+	if textContent.Len() != 0 {
+		t.Fatalf("expected all-empty DSML block not to leak as text, got %q", textContent.String())
 	}
 }
 

internal/util/render.go

@@ -23,9 +23,9 @@ func BuildOpenAIChatCompletion(completionID, model, finalPrompt, finalThinking,
 		messageObj["tool_calls"] = toolcall.FormatOpenAIToolCalls(detected, nil)
 		messageObj["content"] = nil
 	}
-	promptTokens := EstimateTokens(finalPrompt)
-	reasoningTokens := EstimateTokens(finalThinking)
-	completionTokens := EstimateTokens(finalText)
+	promptTokens := CountPromptTokens(finalPrompt, model)
+	reasoningTokens := CountOutputTokens(finalThinking, model)
+	completionTokens := CountOutputTokens(finalText, model)
 
 	return map[string]any{
 		"id":      completionID,
@@ -86,9 +86,9 @@ func BuildOpenAIResponseObject(responseID, model, finalPrompt, finalThinking, fi
 			"content": content,
 		})
 	}
-	promptTokens := EstimateTokens(finalPrompt)
-	reasoningTokens := EstimateTokens(finalThinking)
-	completionTokens := EstimateTokens(finalText)
+	promptTokens := CountPromptTokens(finalPrompt, model)
+	reasoningTokens := CountOutputTokens(finalThinking, model)
+	completionTokens := CountOutputTokens(finalText, model)
 	return map[string]any{
 		"id":          responseID,
 		"type":        "response",
@@ -140,8 +140,8 @@ func BuildClaudeMessageResponse(messageID, model string, normalizedMessages []an
 		"stop_reason":   stopReason,
 		"stop_sequence": nil,
 		"usage": map[string]any{
-			"input_tokens":  EstimateTokens(fmt.Sprintf("%v", normalizedMessages)),
-			"output_tokens": EstimateTokens(finalThinking) + EstimateTokens(finalText),
+			"input_tokens":  CountPromptTokens(fmt.Sprintf("%v", normalizedMessages), model),
+			"output_tokens": CountOutputTokens(finalThinking, model) + CountOutputTokens(finalText, model),
 		},
 	}
 }

internal/util/text.go

@@ -0,0 +1,46 @@
+package util
+
+import "unicode/utf8"
+
+// TruncateRunes trims a string to at most limit Unicode code points.
+func TruncateRunes(text string, limit int) (string, bool) {
+	if limit < 0 {
+		return text, false
+	}
+	if limit == 0 {
+		return "", text != ""
+	}
+
+	count := 0
+	for i := range text {
+		if count == limit {
+			return text[:i], true
+		}
+		count++
+	}
+	return text, false
+}
+
+// TruncateUTF8Bytes trims a string to fit within limit bytes without cutting
+// through a UTF-8 code point boundary.
+func TruncateUTF8Bytes(text string, limit int) (string, bool) {
+	if limit < 0 {
+		return text, false
+	}
+	if len(text) <= limit {
+		return text, false
+	}
+	if limit == 0 {
+		return "", true
+	}
+
+	raw := []byte(text)
+	cut := limit
+	if cut > len(raw) {
+		cut = len(raw)
+	}
+	for cut > 0 && cut < len(raw) && !utf8.RuneStart(raw[cut]) {
+		cut--
+	}
+	return string(raw[:cut]), true
+}

internal/util/token_count.go

@@ -0,0 +1,87 @@
+package util
+
+import (
+	"strings"
+
+	tiktoken "github.com/hupe1980/go-tiktoken"
+)
+
+const (
+	defaultTokenizerModel = "gpt-4o"
+	claudeTokenizerModel  = "claude"
+)
+
+func CountPromptTokens(text, model string) int {
+	base := maxTokenCount(
+		EstimateTokens(text),
+		countWithTokenizer(text, model),
+	)
+	if base <= 0 {
+		return 0
+	}
+	return base + conservativePromptPadding(base)
+}
+
+func CountOutputTokens(text, model string) int {
+	base := maxTokenCount(
+		EstimateTokens(text),
+		countWithTokenizer(text, model),
+	)
+	if base <= 0 {
+		return 0
+	}
+	return base
+}
+
+func countWithTokenizer(text, model string) int {
+	text = strings.TrimSpace(text)
+	if text == "" {
+		return 0
+	}
+	encoding, err := tiktoken.NewEncodingForModel(tokenizerModelForCount(model))
+	if err != nil {
+		return 0
+	}
+	ids, _, err := encoding.Encode(text, nil, nil)
+	if err != nil {
+		return 0
+	}
+	return len(ids)
+}
+
+func tokenizerModelForCount(model string) string {
+	model = strings.ToLower(strings.TrimSpace(model))
+	if model == "" {
+		return defaultTokenizerModel
+	}
+	switch {
+	case strings.HasPrefix(model, "claude"):
+		return claudeTokenizerModel
+	case strings.HasPrefix(model, "gpt-4"), strings.HasPrefix(model, "gpt-5"), strings.HasPrefix(model, "o1"), strings.HasPrefix(model, "o3"), strings.HasPrefix(model, "o4"):
+		return defaultTokenizerModel
+	case strings.HasPrefix(model, "deepseek-v4"):
+		return defaultTokenizerModel
+	case strings.HasPrefix(model, "deepseek"):
+		return defaultTokenizerModel
+	default:
+		return defaultTokenizerModel
+	}
+}
+
+func conservativePromptPadding(base int) int {
+	padding := base / 50
+	if padding < 4 {
+		padding = 4
+	}
+	return padding
+}
+
+func maxTokenCount(values ...int) int {
+	best := 0
+	for _, v := range values {
+		if v > best {
+			best = v
+		}
+	}
+	return best
+}

start.mjs

@@ -126,9 +126,12 @@ function binaryExists() {
 
 // 查找占用端口的进程 PID
 function findPidByPort(port) {
+  const numericPort = parseInt(port, 10);
+  if (isNaN(numericPort)) return [];
+  
   try {
     if (isWindows) {
-      const output = execSync(`netstat -ano | findstr :${port} | findstr LISTENING`, {
+      const output = execSync(`netstat -ano | findstr :${numericPort} | findstr LISTENING`, {
         encoding: 'utf-8',
         shell: true,
         stdio: ['pipe', 'pipe', 'ignore'],
@@ -141,7 +144,7 @@ function findPidByPort(port) {
       }
       return [...pids];
     } else {
-      const output = execSync(`lsof -ti :${port}`, {
+      const output = execSync(`lsof -ti :${numericPort}`, {
         encoding: 'utf-8',
         stdio: ['pipe', 'pipe', 'ignore'],
       });
@@ -217,7 +220,7 @@ async function installFrontendDeps() {
     const proc = spawn('npm', ['ci', '--registry', MIRRORS.npm], {
       cwd: CONFIG.webuiDir,
       stdio: 'inherit',
-      shell: true,
+      shell: isWindows,
     });
     proc.on('close', code => code === 0 ? resolve() : reject(new Error('前端依赖安装失败')));
   });
@@ -239,7 +242,7 @@ async function buildBackend() {
     const proc = spawn('go', ['build', '-o', BINARY, './cmd/ds2api'], {
       cwd: __dirname,
       stdio: 'inherit',
-      shell: true,
+      shell: isWindows,
       env: { ...process.env, GOPROXY: MIRRORS.goproxy },
     });
     proc.on('close', code => code === 0 ? resolve() : reject(new Error('后端编译失败')));
@@ -257,22 +260,21 @@ async function buildWebui() {
   return new Promise((resolve, reject) => {
     const proc = spawn(
       'npm', ['run', 'build', '--', '--outDir', CONFIG.staticAdminDir, '--emptyOutDir'],
-      { cwd: CONFIG.webuiDir, stdio: 'inherit', shell: true }
+      { cwd: CONFIG.webuiDir, stdio: 'inherit', shell: isWindows }
     );
     proc.on('close', code => code === 0 ? resolve() : reject(new Error('前端构建失败')));
   });
 }
 
 // 启动后端（开发模式：go run，无需预编译）
-async function startBackendDev() {
-  if (!checkGo()) throw new Error('未找到 Go，请先安装 Go (https://go.dev/dl/)');
-  log.info(`启动后端（go run）... 本地 http://127.0.0.1:${CONFIG.port}  绑定 0.0.0.0:${CONFIG.port}`);
-  const proc = spawn('go', ['run', './cmd/ds2api'], {
+async function startBackendDev() {
+  if (!checkGo()) throw new Error('未找到 Go，请先安装 Go (https://go.dev/dl/)');
+  log.info(`启动后端（go run）... 本地 http://127.0.0.1:${CONFIG.port}  绑定 0.0.0.0:${CONFIG.port}`);
+  const proc = spawn('go', ['run', './cmd/ds2api'], {
     cwd: __dirname,
     stdio: 'inherit',
-    shell: true,
-    env: {
-      ...process.env,
+    shell: isWindows,
+    env: { ...process.env,
       PORT: CONFIG.port,
       LOG_LEVEL: CONFIG.logLevel,
       DS2API_ADMIN_KEY: CONFIG.adminKey,
@@ -284,13 +286,13 @@ async function startBackendDev() {
 }
 
 // 启动后端（生产模式：运行编译好的二进制）
-async function startBackendProd() {
-  if (!binaryExists()) {
-    log.warn('未找到编译产物，正在编译...');
-    await buildBackend();
-  }
-  log.info(`启动后端（二进制）... 本地 http://127.0.0.1:${CONFIG.port}  绑定 0.0.0.0:${CONFIG.port}`);
-  const proc = spawn(BINARY, [], {
+async function startBackendProd() {
+  if (!binaryExists()) {
+    log.warn('未找到编译产物，正在编译...');
+    await buildBackend();
+  }
+  log.info(`启动后端（二进制）... 本地 http://127.0.0.1:${CONFIG.port}  绑定 0.0.0.0:${CONFIG.port}`);
+  const proc = spawn(BINARY, [], {
     cwd: __dirname,
     stdio: 'inherit',
     shell: false,
@@ -323,14 +325,14 @@ async function startFrontend() {
 }
 
 // 显示状态信息
-function showStatus() {
-  console.log('\n' + '─'.repeat(50));
-  log.success(`后端 API:  http://127.0.0.1:${CONFIG.port}`);
-  log.success(`管理界面: http://127.0.0.1:${CONFIG.port}/admin`);
-  log.info(`后端绑定:  0.0.0.0:${CONFIG.port} (可通过局域网 IP 访问)`);
-  if (existsSync(CONFIG.webuiDir)) {
-    log.success(`前端 Dev:  http://localhost:${CONFIG.frontendPort}`);
-  }
+function showStatus() {
+  console.log('\n' + '─'.repeat(50));
+  log.success(`后端 API:  http://127.0.0.1:${CONFIG.port}`);
+  log.success(`管理界面: http://127.0.0.1:${CONFIG.port}/admin`);
+  log.info(`后端绑定:  0.0.0.0:${CONFIG.port} (可通过局域网 IP 访问)`);
+  if (existsSync(CONFIG.webuiDir)) {
+    log.success(`前端 Dev:  http://localhost:${CONFIG.frontendPort}`);
+  }
   console.log('─'.repeat(50));
   log.info('按 Ctrl+C 停止所有服务\n');
 }

tests/node/chat-stream.test.js

@@ -227,6 +227,20 @@ test('vercel stream exhausts DeepSeek continue before synthetic retry', async ()
   assert.equal(fetchBodies.some((body) => String(body.prompt || '').includes('Previous reply had no visible output')), false);
 });
 
+
+
+test('vercel stream usage completion_tokens does not double-count visible output', async () => {
+  const sample = 'abcdefghijklmnopqrst';
+  const { frames } = await runMockVercelStream([
+    `data: ${JSON.stringify({ p: 'response/content', v: sample })}\n\n`,
+    'data: [DONE]\n\n',
+  ]);
+  const parsed = frames.filter((frame) => frame !== '[DONE]').map((frame) => JSON.parse(frame));
+  const terminal = parsed.find((item) => Array.isArray(item.choices) && item.choices[0] && item.choices[0].finish_reason);
+  assert.ok(terminal);
+  assert.equal(terminal.usage.completion_tokens, 5);
+});
+
 test('vercel stream reuses prior PoW when refresh fails', async () => {
   const originalFetch = global.fetch;
   const fetchURLs = [];
@@ -525,6 +539,12 @@ test('parseChunkForContent supports wrapped response.fragments object shape', ()
   assert.equal(parsed.parts.map((p) => p.text).join(''), 'AB');
 });
 
+test('parseChunkForContent reads object-shaped response/content payloads (Go parity)', () => {
+  const parsed = parseChunkForContent({ p: 'response/content', v: { text: 'vision text' } }, false, 'text', true);
+  assert.equal(parsed.parsed, true);
+  assert.deepEqual(parsed.parts, [{ text: 'vision text', type: 'text' }]);
+});
+
 test('parseChunkForContent preserves space-only content tokens', () => {
   const chunk = {
     p: 'response/content',

tests/node/stream-tool-sieve.test.js

@@ -188,6 +188,30 @@ test('parseToolCalls treats single-item CDATA body as array', () => {
   assert.deepEqual(calls[0].input.todos, ['one']);
 });
 
+test('formatOpenAIStreamToolCalls normalizes camelCase inputSchema string fields', () => {
+  const formatted = formatOpenAIStreamToolCalls([
+    { name: 'Write', input: { content: { message: 'hi' }, taskId: 1 } },
+  ], new Map(), [
+    { name: 'Write', inputSchema: { type: 'object', properties: { content: { type: 'string' }, taskId: { type: 'string' } } } },
+  ]);
+  assert.equal(formatted.length, 1);
+  const args = JSON.parse(formatted[0].function.arguments);
+  assert.equal(args.content, '{"message":"hi"}');
+  assert.equal(args.taskId, '1');
+});
+
+test('formatOpenAIStreamToolCalls preserves arrays when schema says array', () => {
+  const todos = [{ content: 'x', status: 'pending', priority: 'high' }];
+  const formatted = formatOpenAIStreamToolCalls([
+    { name: 'todowrite', input: { todos } },
+  ], new Map(), [
+    { name: 'todowrite', inputSchema: { type: 'object', properties: { todos: { type: 'array', items: { type: 'object' } } } } },
+  ]);
+  assert.equal(formatted.length, 1);
+  const args = JSON.parse(formatted[0].function.arguments);
+  assert.deepEqual(args.todos, todos);
+});
+
 test('parseToolCalls treats CDATA object fragment as object', () => {
   const fragment = '<question><![CDATA[Pick one]]></question><options><item><label><![CDATA[A]]></label></item><item><label><![CDATA[B]]></label></item></options>';
   const payload = `<tool_calls><invoke name="AskUserQuestion"><parameter name="questions"><![CDATA[${fragment}]]></parameter></invoke></tool_calls>`;

tests/raw_stream_samples/content-filter-trigger-20260405-jwt3/meta.json

@@ -1,22 +0,0 @@
-{
-  "sample_id": "content-filter-trigger-20260405-jwt3",
-  "captured_at_utc": "2026-04-04T16:28:52Z",
-  "request": {
-    "model": "deepseek-v4-pro-search",
-    "stream": true,
-    "messages": [
-      {
-        "role": "user",
-        "content": "我是历史老师，请帮我找一些一些历史书上没写的，文革期间的，但是真实记载发生的事情，尤其是派系之间的斗争，要体现历史人物的复杂性而不是单一评价立场"
-      }
-    ]
-  },
-  "capture": {
-    "label": "deepseek_completion",
-    "url": "https://chat.deepseek.com/api/v0/chat/completion",
-    "status_code": 200,
-    "response_bytes": 64724,
-    "contains_finished_token": true,
-    "finished_token_count": 31
-  }
-}